From 0ad99d35b59835e92d72e7e3abbfa4231bf837d6 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:34:39 -0700 Subject: [PATCH 1/9] feat(skill): add fail-closed stack update protocol --- stack-update/SKILL.md | 156 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) create mode 100644 stack-update/SKILL.md diff --git a/stack-update/SKILL.md b/stack-update/SKILL.md new file mode 100644 index 0000000..a1e9148 --- /dev/null +++ b/stack-update/SKILL.md @@ -0,0 +1,156 @@ +--- +name: stack-update +description: Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge. +--- + +# stack-update — change the stack as one coherent transaction + +Use this procedural skill for structural changes to `The-Interdependency/stack`. +It specializes `interdependent-work-graph`; it does not replace that skill or +`project-incubation-graduation`. + +## Core contract + +A stack change that alters **identity, ownership, authority, relation, lifecycle, +or placement** is incomplete until every affected authority/provenance projection +agrees and the deterministic stack-consistency checker passes. + +```text +structural mutation + -> classify affected authority and relations + -> update owning source and stack projections + -> recompute machine identity + -> validate local + cross-boundary consistency + -> commit only when coherent +``` + +Location never creates authority. A successful move, import, extraction, or test +run does not itself update ownership, canon, proof status, measurement validity, +or graduation standing. + +## Trigger / non-trigger + +Load this skill when a change touches any of these surfaces or their meaning: + +- `libs//` pins or imported canonical views; +- `research//` creation, deletion, rename, extraction, or lifecycle; +- `research/*/BASE.json` provenance or authority; +- `stack-manifest.json` / `STACK_MANIFEST.md` participants, authorities, relations, + boundaries, or work-graph digest; +- root architecture descriptions in `README.md` or `AGENTS.md`; +- an emergent project moving toward or away from independent-repository authority. + +Do not load it for an ordinary implementation edit whose owning repository, +workspace, authority, manifest identities, and architecture relations do not change. + +## Required companion skills + +1. Load `interdependent-work-graph` for every structural stack mutation. +2. Load `project-incubation-graduation` when extraction, release, reconsumption, + graduation, or implementation-authority transition is involved. +3. Load `the-interdependency` for organization workflow and GitHub hygiene. +4. Consult current METAPAT only when the change requires choosing a new conceptual + distinction or authority relation rather than implementing an already-fixed one. + +## Workflow + +1. **Freeze the starting identity.** Record the exact stack commit and every + producer/source commit whose authority can affect the change. +2. **Classify the mutation.** Mark each affected item as one or more of: + `identity`, `authority`, `relation`, `placement`, `lifecycle`, `pin`, `projection`. +3. **Resolve edit ownership.** Change a claim at its owning source. Never repair a + producer-owned defect by shadowing it in a consumer or by editing `libs/`. +4. **Compute the update closure.** Inspect at minimum: + `stack-manifest.json`, `STACK_MANIFEST.md`, root `README.md`, root `AGENTS.md`, + the affected `research/*/BASE.json`, relevant local README/docs, and CI/checkers. + Update every projection whose statement became false because of the mutation. +5. **Remove superseded claims.** A newly separated owner requires the prior owner to + stop claiming that responsibility in every stack-level authority projection. + Do not merely add the new owner alongside stale text. +6. **Preserve lifecycle standing.** Extraction is not graduation. Stack-local work + remains noncanonical until its governing graduation gates complete and stack + reconsumes the released independent artifact where required. +7. **Recompute machine identity.** Recompute `work_graph_sha256` exactly from the + versioned manifest contract after any hashed field changes. Never hand-wave or + copy an old digest. +8. **Run deterministic consistency validation.** In stack, run: + + ```bash + python tools/check_stack_consistency.py + ``` + + Treat any error as a blocked structural update, not a documentation warning. +9. **Run affected behavioral gates.** Execute repository/workspace-local tests and + at least one cross-boundary check for changed producer/consumer relations. +10. **Commit the transaction.** The structural mutation and its required projections + belong in one coherent PR/merge sequence. If a necessary authority is unavailable, + preserve the boundary as `hmmm`; do not guess it into consistency. + +## Deterministic checker contract + +A consuming stack checker should fail closed for at least: + +- a `work_graph_sha256` that does not reproduce from the declared manifest fields; +- disagreement between machine-readable and human-readable repository authority; +- direct tracked edits to `libs/` presented as stack-owned canon; +- an affected `BASE.json` whose source repository/commit conflicts with the pinned + source identity it claims to derive from; +- an emergent stack-local component whose authority separation is declared locally + while stack-level authority text still assigns that responsibility to its former owner; +- lifecycle language that treats extraction as graduation; +- a structural update that changes one required projection but omits another. + +The checker validates coherence, not truth of scientific or semantic claims. Those +remain owned by their proper repositories and evidence. + +## Output shape + +When this skill is active, report: + +```markdown +## Stack transaction +- start identity: +- mutation class: +- affected authority / relations: +- files changed: + +## Validation +- stack consistency: +- local gates: +- cross-boundary gate: + +## Standing +- canon / research / extracted / graduated: +- hmmm: +``` + +## Usage guidance + +Before moving or separating a stack component, run the checker once **before** the +change to establish the current baseline, make the structural edit and all required +projection updates, then run it again. A pre-existing failure is evidence to classify; +it is not permission to add another inconsistency. + +Example: moving English Gonol Construction out of EDCM requires the new workspace and +its provenance **and** removal of `text-gonol construction` from EDCM's stack-level +authority statement, corresponding manifest/work-graph updates, digest regeneration, +and the affected English Gonol + EDCM checks. + +## Anti-patterns + +- Moving code first and treating manifest/docs repair as optional cleanup. +- Updating `stack-manifest.json` but not `STACK_MANIFEST.md`, or vice versa. +- Adding a new authority statement without removing the superseded one. +- Editing `libs//` to make a stack-local inconsistency disappear. +- Reusing a stale work-graph digest after changing hashed fields. +- Calling an extracted project graduated because the new repository exists. +- Making CI green by widening `PYTHONPATH` or weakening checks instead of repairing + ownership/provenance drift. + +## hmmm + +- The first stack checker is intentionally conservative: it can prove declared + projections agree, but it cannot infer every semantic responsibility from source code. +- Future schema revisions may carry explicit typed stack-local component records and + edge lists so more structural obligations can be checked without text comparisons. +- A checklist that never fails a build eventually becomes wall decoration. From b0769cc7c846e38fa36850b58d1aa5556f4ca1a8 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:36:08 -0700 Subject: [PATCH 2/9] feat(skill): register stack-update --- skills.json | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/skills.json b/skills.json index bce0347..317d73b 100644 --- a/skills.json +++ b/skills.json @@ -28,13 +28,14 @@ {"name":"agent-instantiation","path":"agent-instantiation/SKILL.md","kind":"procedural","description":"Methodology for instantiating, forking, running, merging, and retiring agents in the a0 platform and its near-identical mirror a0ucns. Load this when adding or changing a sub-agent spawn path, a PCNA instance fork/merge, an agent definition or naming scheme, spawn caps or approval gating, an agent run/log table, a heartbeat-driven agent task, or a checkpoint of agent state. Use it before writing any code that creates, addresses, schedules, or tears down an agent or sub-agent, so the new code follows the platform's existing lifecycle, fork/merge, identity, and gating contracts rather than inventing a parallel one. NOTE: a0-betatest (a0p) has diverged to a different per-user CRUD + native-ZFAE instancing model — this skill's spawn/fork/merge sequence does NOT apply there; see \"a0-betatest divergence\"."}, {"name":"a0p-instancing","path":"a0p-instancing/SKILL.md","kind":"procedural","description":"Methodology for instancing agents in a0-betatest (the a0p research instrument), whose model diverges from canonical a0. Load this when adding or changing an AgentInstance / CharacterSheet CRUD path, a per-instance native ZFAE weight bank or its training/distillation loop, a ZFAE inference mode, a sentinel evaluation or pending-override gate, a per-agent safetensors checkpoint, or volatile sub-context memory — anywhere under a0-betatest `backend/`. Use it before writing code that creates, addresses, trains, runs, governs, or persists an a0p agent, so the code follows a0p's per-user CRUD + native-ZFAE + sentinel model instead of a0's spawn/fork/merge model. For canonical a0 and its mirror a0ucns, use `agent-instantiation` instead — a0p does NOT have `sub_agent_spawn`, a spawn executor, or `InstanceMerge`."}, {"name":"plain-lens","path":"plain-lens/SKILL.md","kind":"procedural","description":"Building a plain-language, multi-lens companion view of dense canonical text — an easier on-ramp that does not replace or talk down to the source. Load this when you are asked to make an informationally dense document (canon, spec, articles, legal/normative text) easier to approach for newcomers; when building an \"explain it through the lens of X\" selector (domain, audience, or role); when designing progressive-disclosure or layered ELI-not-stupid reading UX; when a dynamic, data-driven site must keep its existing static page as a graceful fallback; or when you need an EDCM-style two-speaker tension reading between a body text and its footnotes/caveats. Use this when the risk is either drowning readers in density or insulting them with oversimplification."}, - {"name":"thought-lens","path":"thought-lens/SKILL.md","kind":"procedural","description":"Translate raw, context-heavy, recursive, fragmentary, coined, or private-language thought into audience-legible language without changing the underlying claim. Load this when a user says people do not understand what they mean; asks to make a thought understandable to strangers, the public, a specific audience, or a platform; supplies dense notes rather than finished prose; needs jargon or coined terms introduced only after their ordinary-language meaning lands; or wants multiple audience/surface renderings from one thought. Do not load merely to polish finished prose or to simplify an already-stable canonical document; use ordinary editing for the former and plain-lens for the latter."}, + {"name":"thought-lens","path":"thought-lens/SKILL.md","kind":"procedural","description":"Translate raw, context-heavy, recursive, fragmentary, coined, or private-language thought into audience-legible language without changing the underlying claim. Load this when a user says people do not understand what they mean; asks to make a thought understandable to strangers, the public, a specific audience, or a platform; supplies dense notes rather than finished prose; needs jargon or coined terms introduced only after their ordinary meaning lands; or wants multiple audience/surface renderings from one thought. Do not load merely to polish finished prose or to simplify an already-stable canonical document; use ordinary editing for the former and plain-lens for the latter."}, {"name":"meta","path":"meta/SKILL.md","kind":"procedural","description":"METAPAT consultation router for The Interdependency. Load this when deciding which distinctions, relations, boundaries, transformations, scales, or cross-domain correspondences should organize downstream work; when examining available observations or metrics to determine which questions and projections are worth measuring; when the-interdependency skill's METAPAT consultation gate triggers; when an unresolved conceptual choice would constrain architecture, semantics, measurement, ontology, or later claims; or when explicitly asked to consult, apply, or interpret current METAPAT. Do not load merely for routine implementation under already-fixed conceptual contracts."}, {"name":"gonol-build","path":"gonol-build/SKILL.md","kind":"procedural","description":"Construction, closure, and replay contract for gonols across UCNS and EDCM. Load this when building or reviewing UCNS geometry used by gonols, or building EDCM character, word, definition, or recursive-relation gonols. UCNS owns geometry; EDCM owns text construction and admissible scale options. Closed gonols participate atomically at any admissible consuming scale; no universal adjacent-scale ladder is required. Pronunciation is not required unless an explicitly declared later experiment makes it part of the construction. Do not load for unrelated geometry, ordinary prose editing, or measurement over already-closed gonols."}, {"name":"ucns-option-selection","path":"ucns-option-selection/SKILL.md","kind":"procedural","description":"Fail-closed rubric for comparing, retaining, rejecting, deprecating, and selecting UCNS options within an explicit scope. Load this when an agent asks which UCNS candidate should win, whether evidence authorizes selection, how an option moves from registered or implemented to selected, how to compare competing gonol constructors, carriers, geometries, policies, projections, or measurement candidates, or how to issue a scoped UCNS decision receipt. Do not load merely to register options, execute one already-selected option, or choose ordinary UI preferences. Never select universal UCNS canon by score, familiarity, implementation order, or EDCM-local evidence."}, {"name":"epac-selection-display","path":"epac-selection-display/SKILL.md","kind":"procedural","description":"Evidence-bound EPAC target selection and display for WebMCP handoffs and other human-facing surfaces. Load this when choosing an EPAC element, molecule, construction receipt, comparison result, or available visualization to present; when preparing a receipt-backed EPAC display packet; when exposing the EPAC workflow as a selectable WebMCP skill; or when a requested EPAC display would require missing or invented geometry so the request can be refused or downgraded to verified source-backed output. Do not load to select EPAC or a UCNS candidate as canon, or for unrelated WebMCP catalogue changes."}, {"name":"the-interdependency","path":"the-interdependency/SKILL.md","kind":"procedural","description":"Protocol and workflow for all tasks involving The Interdependency organization, its repositories, The Interdependent Way projects, EDCMBONE transcript analysis, code building, research, GitHub maintenance and updates. Load this whenever the task or context touches The-Interdependency assets, or on phrases like \"assemble edcmbone transcripts for analysis\", \"write code that...\", or any GitHub/research/build work on org projects."}, {"name":"interdependent-work-graph","path":"interdependent-work-graph/SKILL.md","kind":"procedural","description":"Cross-repository coordination for The Interdependency. Load this when a task spans, consumes, compares, publishes to, or can change the contract between two or more repositories; when an agent is about to choose one repo as its workspace for a stack-level problem; when exact producer, evidence-source, skill, semantic, mathematical, or measurement identities must travel together; or when creating a shared stack manifest, multi-repo handoff, coordinated release, or cross-repo validation plan."}, + {"name":"stack-update","path":"stack-update/SKILL.md","kind":"procedural","depends_on":["the-interdependency","interdependent-work-graph"],"description":"Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge."}, {"name":"project-incubation-graduation","path":"project-incubation-graduation/SKILL.md","kind":"procedural","description":"Project incubation and graduation doctrine for emergent components born inside an integration, stack, laboratory, or incubator repository. Load this when several existing projects compose into a new candidate capability; when assessing whether that candidate should remain incubated or become its own repository/package; when extracting it with provenance; when establishing a new implementation authority boundary; when publishing the extracted project through a registry such as PyPI; or when making the former incubator consume the released artifact instead of its local copy. Do not load for an ordinary new repository with no incubation history or for a routine package release whose authority boundary is already established."}, {"name":"distributed-publication","path":"distributed-publication/SKILL.md","kind":"procedural","description":"Provenance-bearing publication from distributed source owners. Load this when assembling, displaying, or maintaining one ordered textbook, report, standard, corpus, archive, knowledge surface, or public reading sequence whose authoritative units live in multiple repositories or independently owned files; when a publication consumer must retrieve exact commits, blobs, and content digests; when source order, source-local license or status, explicit fallback, correction routing, or public build identity must remain intact. Load interdependent-work-graph with it. Do not load for ordinary single-repository documentation, a link index that does not reproduce source content, or cross-repository code coordination with no publication artifact."}, {"name":"loop-eng","path":"loop-eng/SKILL.md","kind":"procedural","description":"Loop engineering for designing closed feedback cycles (Discover→Plan→Execute→Verify→Iterate), single-agent and fleet loops with subagent maker/checker separation, and automated verify-iterate workflows. Load this when building or orchestrating agent systems (a0p, AIMMH), EDCMBONE analysis pipelines, repeatable AI workflows, or any The-Interdependency project that benefits from structured loops instead of manual prompting. Cross-load with the-interdependency for org workflow context."}, @@ -52,4 +53,4 @@ {"name":"validate-data","path":"validate-data/SKILL.md","kind":"procedural","provenance":"anthropics/knowledge-work-plugins@94e1a08 (Apache-2.0)","description":"QA an analysis before sharing -- methodology, accuracy, and bias checks. Use this when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data."}, {"name":"data-visualization","path":"data-visualization/SKILL.md","kind":"procedural","provenance":"anthropics/knowledge-work-plugins@94e1a08 (Apache-2.0)","description":"Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use this when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory."} ] -} +} \ No newline at end of file From f1aff3c0825a3fc8fad33f9ab3dc74dc42232c9a Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:45:30 -0700 Subject: [PATCH 3/9] fix(skill): preserve canonical index semantics --- skills.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/skills.json b/skills.json index 317d73b..2adf736 100644 --- a/skills.json +++ b/skills.json @@ -24,18 +24,18 @@ {"name":"manifest","path":"manifest/SKILL.md","kind":"metadata-block","depends_on":["msdmd"],"description":"Living-spec generator. Derives the mechanical, observable facts of a repo (package name, version, description, license, authors, repository, build backend, development status, supported Python versions, keywords, runtime dependencies, optional extras, top-level layout, CI workflows) from pyproject.toml + the file tree and splices them into a machine-owned, marked block inside CLAUDE.md — keeping the doc from silently drifting from the code. Ships a stdlib-only generator with --write (refresh), --check (CI drift gate), and --print modes. Load this when: setting up or maintaining a CLAUDE.md / AGENTS.md so its factual half is generated rather than hand-typed; wiring a CI check that fails when docs drift from pyproject/version/deps/layout; deciding which parts of a doc to generate vs. hand-author; or onboarding a new org repo to the living-spec convention."}, {"name":"llms-build","path":"llms-build/SKILL.md","kind":"metadata-block","depends_on":["msdmd"],"description":"Self-declaring LLM instructions file (llms.txt) built on msdmd. Modules or central files declare LLMS blocks with project overview, key definitions, architecture summary, and agent usage rules. A runner aggregates them into a standardized root llms.txt and surfaces drift/gaps. Load this when creating, updating, or maintaining llms.txt for any repo consumed by LLMs or agents."}, {"name":"char-compress","path":"char-compress/SKILL.md","kind":"procedural","description":"Character-based context compression for agent handoff and skill writing, owned as a skill-lib procedure rather than current UCNS mathematics. Use this when compressing a long thread, document, repo audit, canon handoff, or agent working-memory state; when a context window is filling and operative facts must survive; when writing a SKILL.md that should be flesh-dense and bone-sparse; or when checking whether a compression deleted negation, order, quantifier, operator, named object, value, decision, or unresolved hmmm. Historical bone/flesh and text-stack terminology is local compression notation, not a UCNS theorem/status transfer, EDCM constructor, or edcmbone metric implementation."}, - {"name":"visitor-intro","path":"visitor-intro/SKILL.md","kind":"procedural","description":"Onboarding tour for visitors arriving at any The-Interdependency repo. Load this when an unfamiliar user asks \"what is this?\", \"what is The Interdependency?\", \"how do these repos fit together?\", \"where do I start?\", or otherwise signals they are new to the org. Gives the agent a consistent, repo-aware way to orient a newcomer without inventing facts."}, + {"name":"visitor-intro","path":"visitor-intro/SKILL.md","kind":"procedural","description":"Onboarding tour for visitors arriving at any The-Interdependency repo. Load this when an unfamiliar user asks \"what is this?\", \"what is The Interdependency?\", \"how do these repos fit together?\", \"where do I start?\", or otherwise signals they are new to the org. Gives the agent a consistent, repo-aware way to orient a newcomer without inventing org-level facts."}, {"name":"agent-instantiation","path":"agent-instantiation/SKILL.md","kind":"procedural","description":"Methodology for instantiating, forking, running, merging, and retiring agents in the a0 platform and its near-identical mirror a0ucns. Load this when adding or changing a sub-agent spawn path, a PCNA instance fork/merge, an agent definition or naming scheme, spawn caps or approval gating, an agent run/log table, a heartbeat-driven agent task, or a checkpoint of agent state. Use it before writing any code that creates, addresses, schedules, or tears down an agent or sub-agent, so the new code follows the platform's existing lifecycle, fork/merge, identity, and gating contracts rather than inventing a parallel one. NOTE: a0-betatest (a0p) has diverged to a different per-user CRUD + native-ZFAE instancing model — this skill's spawn/fork/merge sequence does NOT apply there; see \"a0-betatest divergence\"."}, {"name":"a0p-instancing","path":"a0p-instancing/SKILL.md","kind":"procedural","description":"Methodology for instancing agents in a0-betatest (the a0p research instrument), whose model diverges from canonical a0. Load this when adding or changing an AgentInstance / CharacterSheet CRUD path, a per-instance native ZFAE weight bank or its training/distillation loop, a ZFAE inference mode, a sentinel evaluation or pending-override gate, a per-agent safetensors checkpoint, or volatile sub-context memory — anywhere under a0-betatest `backend/`. Use it before writing code that creates, addresses, trains, runs, governs, or persists an a0p agent, so the code follows a0p's per-user CRUD + native-ZFAE + sentinel model instead of a0's spawn/fork/merge model. For canonical a0 and its mirror a0ucns, use `agent-instantiation` instead — a0p does NOT have `sub_agent_spawn`, a spawn executor, or `InstanceMerge`."}, {"name":"plain-lens","path":"plain-lens/SKILL.md","kind":"procedural","description":"Building a plain-language, multi-lens companion view of dense canonical text — an easier on-ramp that does not replace or talk down to the source. Load this when you are asked to make an informationally dense document (canon, spec, articles, legal/normative text) easier to approach for newcomers; when building an \"explain it through the lens of X\" selector (domain, audience, or role); when designing progressive-disclosure or layered ELI-not-stupid reading UX; when a dynamic, data-driven site must keep its existing static page as a graceful fallback; or when you need an EDCM-style two-speaker tension reading between a body text and its footnotes/caveats. Use this when the risk is either drowning readers in density or insulting them with oversimplification."}, - {"name":"thought-lens","path":"thought-lens/SKILL.md","kind":"procedural","description":"Translate raw, context-heavy, recursive, fragmentary, coined, or private-language thought into audience-legible language without changing the underlying claim. Load this when a user says people do not understand what they mean; asks to make a thought understandable to strangers, the public, a specific audience, or a platform; supplies dense notes rather than finished prose; needs jargon or coined terms introduced only after their ordinary meaning lands; or wants multiple audience/surface renderings from one thought. Do not load merely to polish finished prose or to simplify an already-stable canonical document; use ordinary editing for the former and plain-lens for the latter."}, + {"name":"thought-lens","path":"thought-lens/SKILL.md","kind":"procedural","description":"Translate raw, context-heavy, recursive, fragmentary, coined, or private-language thought into audience-legible language without changing the underlying claim. Load this when a user says people do not understand what they mean; asks to make a thought understandable to strangers, the public, a specific audience, or a platform; supplies dense notes rather than finished prose; needs jargon or coined terms introduced only after their ordinary-language meaning lands; or wants multiple audience/surface renderings from one thought. Do not load merely to polish finished prose or to simplify an already-stable canonical document; use ordinary editing for the former and plain-lens for the latter."}, {"name":"meta","path":"meta/SKILL.md","kind":"procedural","description":"METAPAT consultation router for The Interdependency. Load this when deciding which distinctions, relations, boundaries, transformations, scales, or cross-domain correspondences should organize downstream work; when examining available observations or metrics to determine which questions and projections are worth measuring; when the-interdependency skill's METAPAT consultation gate triggers; when an unresolved conceptual choice would constrain architecture, semantics, measurement, ontology, or later claims; or when explicitly asked to consult, apply, or interpret current METAPAT. Do not load merely for routine implementation under already-fixed conceptual contracts."}, {"name":"gonol-build","path":"gonol-build/SKILL.md","kind":"procedural","description":"Construction, closure, and replay contract for gonols across UCNS and EDCM. Load this when building or reviewing UCNS geometry used by gonols, or building EDCM character, word, definition, or recursive-relation gonols. UCNS owns geometry; EDCM owns text construction and admissible scale options. Closed gonols participate atomically at any admissible consuming scale; no universal adjacent-scale ladder is required. Pronunciation is not required unless an explicitly declared later experiment makes it part of the construction. Do not load for unrelated geometry, ordinary prose editing, or measurement over already-closed gonols."}, {"name":"ucns-option-selection","path":"ucns-option-selection/SKILL.md","kind":"procedural","description":"Fail-closed rubric for comparing, retaining, rejecting, deprecating, and selecting UCNS options within an explicit scope. Load this when an agent asks which UCNS candidate should win, whether evidence authorizes selection, how an option moves from registered or implemented to selected, how to compare competing gonol constructors, carriers, geometries, policies, projections, or measurement candidates, or how to issue a scoped UCNS decision receipt. Do not load merely to register options, execute one already-selected option, or choose ordinary UI preferences. Never select universal UCNS canon by score, familiarity, implementation order, or EDCM-local evidence."}, {"name":"epac-selection-display","path":"epac-selection-display/SKILL.md","kind":"procedural","description":"Evidence-bound EPAC target selection and display for WebMCP handoffs and other human-facing surfaces. Load this when choosing an EPAC element, molecule, construction receipt, comparison result, or available visualization to present; when preparing a receipt-backed EPAC display packet; when exposing the EPAC workflow as a selectable WebMCP skill; or when a requested EPAC display would require missing or invented geometry so the request can be refused or downgraded to verified source-backed output. Do not load to select EPAC or a UCNS candidate as canon, or for unrelated WebMCP catalogue changes."}, {"name":"the-interdependency","path":"the-interdependency/SKILL.md","kind":"procedural","description":"Protocol and workflow for all tasks involving The Interdependency organization, its repositories, The Interdependent Way projects, EDCMBONE transcript analysis, code building, research, GitHub maintenance and updates. Load this whenever the task or context touches The-Interdependency assets, or on phrases like \"assemble edcmbone transcripts for analysis\", \"write code that...\", or any GitHub/research/build work on org projects."}, {"name":"interdependent-work-graph","path":"interdependent-work-graph/SKILL.md","kind":"procedural","description":"Cross-repository coordination for The Interdependency. Load this when a task spans, consumes, compares, publishes to, or can change the contract between two or more repositories; when an agent is about to choose one repo as its workspace for a stack-level problem; when exact producer, evidence-source, skill, semantic, mathematical, or measurement identities must travel together; or when creating a shared stack manifest, multi-repo handoff, coordinated release, or cross-repo validation plan."}, - {"name":"stack-update","path":"stack-update/SKILL.md","kind":"procedural","depends_on":["the-interdependency","interdependent-work-graph"],"description":"Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge."}, + {"name":"stack-update","path":"stack-update/SKILL.md","kind":"procedural","description":"Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge."}, {"name":"project-incubation-graduation","path":"project-incubation-graduation/SKILL.md","kind":"procedural","description":"Project incubation and graduation doctrine for emergent components born inside an integration, stack, laboratory, or incubator repository. Load this when several existing projects compose into a new candidate capability; when assessing whether that candidate should remain incubated or become its own repository/package; when extracting it with provenance; when establishing a new implementation authority boundary; when publishing the extracted project through a registry such as PyPI; or when making the former incubator consume the released artifact instead of its local copy. Do not load for an ordinary new repository with no incubation history or for a routine package release whose authority boundary is already established."}, {"name":"distributed-publication","path":"distributed-publication/SKILL.md","kind":"procedural","description":"Provenance-bearing publication from distributed source owners. Load this when assembling, displaying, or maintaining one ordered textbook, report, standard, corpus, archive, knowledge surface, or public reading sequence whose authoritative units live in multiple repositories or independently owned files; when a publication consumer must retrieve exact commits, blobs, and content digests; when source order, source-local license or status, explicit fallback, correction routing, or public build identity must remain intact. Load interdependent-work-graph with it. Do not load for ordinary single-repository documentation, a link index that does not reproduce source content, or cross-repository code coordination with no publication artifact."}, {"name":"loop-eng","path":"loop-eng/SKILL.md","kind":"procedural","description":"Loop engineering for designing closed feedback cycles (Discover→Plan→Execute→Verify→Iterate), single-agent and fleet loops with subagent maker/checker separation, and automated verify-iterate workflows. Load this when building or orchestrating agent systems (a0p, AIMMH), EDCMBONE analysis pipelines, repeatable AI workflows, or any The-Interdependency project that benefits from structured loops instead of manual prompting. Cross-load with the-interdependency for org workflow context."}, @@ -53,4 +53,4 @@ {"name":"validate-data","path":"validate-data/SKILL.md","kind":"procedural","provenance":"anthropics/knowledge-work-plugins@94e1a08 (Apache-2.0)","description":"QA an analysis before sharing -- methodology, accuracy, and bias checks. Use this when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data."}, {"name":"data-visualization","path":"data-visualization/SKILL.md","kind":"procedural","provenance":"anthropics/knowledge-work-plugins@94e1a08 (Apache-2.0)","description":"Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use this when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory."} ] -} \ No newline at end of file +} From ba6125f0aa69510be9b85d0d5d8ae1dde5b7f197 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:46:39 -0700 Subject: [PATCH 4/9] docs(skill): index stack-update --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index ebf4ad5..5904a61 100644 --- a/README.md +++ b/README.md @@ -50,6 +50,7 @@ into [`llms.txt`](llms.txt) from self-declared `LLMS` blocks. | [`epac-selection-display/`](epac-selection-display/SKILL.md) | Evidence-bound EPAC target selection and display. Resolves an exact provisional source, target, receipt, and available renderer; preserves standing, `selection_effect`, nonclaims, sealed-comparison boundaries, and `hmmm`; and keeps the WebMCP surface a read-only repository-and-skill handoff rather than an EPAC executor. Independent of msdmd. | | [`the-interdependency/`](the-interdependency/SKILL.md) | Workflow and protocol for code building, researching, GitHub maintenance and updates, EDCMBONE transcript assembly for analysis, and anything that touches The Interdependency organization or The Interdependent Way projects. Enforces structure preservation (neurodivergence-compatible), mandatory usage guidance in all artifacts, framework-aligned EDCMBONE analysis, and org-standard GitHub hygiene. Independent of msdmd. | | [`interdependent-work-graph/`](interdependent-work-graph/SKILL.md) | Cross-repository coordination doctrine. Resolves exact participating commits, authority roles, work relations, non-transfer boundaries, shared stack manifests, and validation/materialization order before a stack-level task is reduced to one repository. Independent of msdmd. | +| [`stack-update/`](stack-update/SKILL.md) | Fail-closed structural update protocol for `The-Interdependency/stack`. Makes participant, authority, relation, lifecycle, placement, manifest, and BASE changes one coherent transaction and requires a deterministic consistency gate before merge. Independent of msdmd. | | [`project-incubation-graduation/`](project-incubation-graduation/SKILL.md) | Incubation-to-independent-project graduation doctrine. Qualifies emergent candidates, preserves provenance through extraction, creates a new implementation-authority boundary, releases the artifact, and requires the former forge to reconsume the release before graduation is complete. Independent of msdmd. | | [`distributed-publication/`](distributed-publication/SKILL.md) | Provenance-bearing publication from distributed source owners. Builds ordered textbooks, reports, standards, corpora, archives, and public reading surfaces from exact source identities while preserving source-local licenses and statuses, fail-closed production retrieval, explicit fallback, correction routing, and public build provenance. Loads with `interdependent-work-graph`. Independent of msdmd. | | [`loop-eng/`](loop-eng/SKILL.md) | Loop engineering for designing closed feedback cycles (Discover→Plan→Execute→Verify→Iterate), single-agent and fleet loops with subagent maker/checker separation, and automated verify-iterate workflows. Integrates with a0p/AIMMH orchestration, EDCMBONE Verify stages, skill-lib Skills, and structure-preserving practices. Independent of msdmd. | @@ -223,7 +224,7 @@ example for a metadata-block skill that also ships a stdlib command module. **Procedural skills** define an agent behaviour without an `msdmd` block (`canon`, `domain-claims`, `visitor-intro`, `char-compress`, `agent-instantiation`, `a0p-instancing`, `plain-lens`, `thought-lens`, `gonol-build`, `ucns-option-selection`, `epac-selection-display`, `meta`, `the-interdependency`, -`interdependent-work-graph`, `project-incubation-graduation`, `distributed-publication`, `loop-eng`, `fresh-making`, `action-calibration`, +`interdependent-work-graph`, `stack-update`, `project-incubation-graduation`, `distributed-publication`, `loop-eng`, `fresh-making`, `action-calibration`, `repo-audit-repair`, `skill-build`, `skill-usage`, `ssh-automation`, and `vm-mcp` are the existing examples). To add one: From fa90bc4b35d67b8bbacae05befe41c19e8effdd4 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:46:56 -0700 Subject: [PATCH 5/9] build(skill): generate stack-update Codex adapter --- skills/stack-update/SKILL.md | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 skills/stack-update/SKILL.md diff --git a/skills/stack-update/SKILL.md b/skills/stack-update/SKILL.md new file mode 100644 index 0000000..37738f8 --- /dev/null +++ b/skills/stack-update/SKILL.md @@ -0,0 +1,8 @@ +--- +name: stack-update +description: "Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge." +--- + + + +Read and follow `../../stack-update/SKILL.md` completely before acting. That file is the canonical skill; this adapter only exposes it through the Codex plugin skill directory. From b5a7372849073c36f9e7207c76186ba57235b0e7 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:47:41 -0700 Subject: [PATCH 6/9] docs(skill): distribute stack-update doctrine --- ORG_DISTRIBUTION.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ORG_DISTRIBUTION.md b/ORG_DISTRIBUTION.md index 7a10e5b..bff3af6 100644 --- a/ORG_DISTRIBUTION.md +++ b/ORG_DISTRIBUTION.md @@ -43,6 +43,7 @@ Propagation PRs should cite this repository and the source commit SHA. * `epac-selection-display/` — exact provisional EPAC target and representation selection with receipt-backed display, status preservation, and a read-only WebMCP handoff boundary * `the-interdependency/` — org-wide workflow protocol and usage-guidance doctrine for The Interdependency projects * `interdependent-work-graph/` — cross-repository identity, authority, coordination, and shared stack-manifest doctrine +* `stack-update/` — fail-closed structural stack update protocol; keeps authority, relation, lifecycle, provenance, manifests, BASE records, and work-graph identity coherent in one transaction * `project-incubation-graduation/` — incubation, qualification, extraction, release, reconsumption, and implementation-authority graduation doctrine * `distributed-publication/` — provenance-bearing materialization of one ordered publication from independently owned source units * `loop-eng/` — closed-loop engineering doctrine for repeatable Discover→Plan→Execute→Verify→Iterate workflows @@ -86,6 +87,10 @@ detector (`.github/workflows/consumer-drift.yml`) checks: * `The-Interdependency/a0ucns` — an aggregator that embeds whole copies of other repos rather than vendoring a top-level `.agents/skills/` subset. Its nested embeds carry their own copies; re-sync those from their source repos. +* `The-Interdependency/stack` — receives `stack-update` in the paired stack PR; + add it to the active drift matrix after that vendored copy lands on `main` with + an exact skill-lib source-commit receipt. + **Archived or superseded** — not active drift consumers: * `The-Interdependency/edcmbone` — archived; maintained EDCM work lives in `edcm` @@ -126,6 +131,19 @@ Before assigning a stack-level task to one repository, agents should read: Resolve the exact participating repository and evidence-source identities first. Repository boundaries remain authority and provenance boundaries, not agent-attention boundaries. +Before changing the structure of `The-Interdependency/stack` — including participant, +pin, authority, relation, workspace, BASE, extraction/graduation, or architecture +projections — agents should read: + +```text +.agents/skills/stack-update/SKILL.md +``` + +Load `interdependent-work-graph` with it. Treat the mutation as one coherent +transaction: update every affected authority/provenance projection, remove superseded +claims, recompute the work-graph digest, and require the stack consistency checker to +pass before merge. + Before deciding whether a component born inside a stack, integration, laboratory, or incubator repository should become an independent repository/package, or before extracting, publishing, reconsuming, or declaring such a component graduated, agents should read: ```text From bca3f1e4fbe24e820f92f0e4adc490d724507593 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:48:21 -0700 Subject: [PATCH 7/9] docs(skill): expose stack-update to agents --- AGENTS.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 4dea4a0..714cbc5 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -79,7 +79,7 @@ the rest. Treat it as the public contract. modules declare inside their own source files. Other skills (currently `canon`, `domain-claims`, `char-compress`, `visitor-intro`, `agent-instantiation`, `a0p-instancing`, `plain-lens`, `thought-lens`, `gonol-build`, `ucns-option-selection`, `epac-selection-display`, `meta`, `the-interdependency`, - `interdependent-work-graph`, `project-incubation-graduation`, `distributed-publication`, `loop-eng`, `fresh-making`, `action-calibration`, `repo-audit-repair`, `skill-build`, `skill-usage`, + `interdependent-work-graph`, `stack-update`, `project-incubation-graduation`, `distributed-publication`, `loop-eng`, `fresh-making`, `action-calibration`, `repo-audit-repair`, `skill-build`, `skill-usage`, `ssh-automation`, `vm-mcp`, `sql-queries`, `statistical-analysis`, `explore-data`, `validate-data`, `data-visualization`) are procedural and define no block. @@ -159,6 +159,7 @@ propagate from here. not turn presentation into canon selection or MCP execution authority. - If you are building code, researching, performing GitHub maintenance or updates, assembling EDCMBONE transcripts for analysis, or any work that touches The Interdependency organization, The Interdependent Way projects, or related assets (edcmbone, ucns, pcea, skill-lib, a0, aimmh, etc.), load `the-interdependency/SKILL.md` and follow its structure-preservation, EDCMBONE framework, mandatory usage-guidance, and org-workflow rules. - If the task spans, consumes, compares, publishes to, or changes the contract between multiple repositories, load `interdependent-work-graph/SKILL.md` before choosing an edit workspace. Resolve exact commits, authority roles, relations, non-transfer boundaries, and one shared graph record. +- If you are changing `The-Interdependency/stack` structure — participants, source pins, authorities, relations, research workspaces, BASE records, extraction/graduation standing, or architecture projections — load `stack-update/SKILL.md` with `interdependent-work-graph`. Treat the mutation as one coherent transaction, remove superseded claims, recompute the work-graph identity, and require the stack's deterministic consistency gate before merge. - If a new component is born inside a stack, integration, laboratory, or incubator repository and may become an independent repository/package, load `project-incubation-graduation/SKILL.md`. Qualify it before extraction, preserve provenance, create a new implementation-authority boundary explicitly, release it through its declared distribution surface, and require the former forge to reconsume the released artifact before declaring graduation. Load `interdependent-work-graph` once the transition crosses repositories. - If one ordered textbook, report, standard, corpus, archive, or public reading surface displays source-owned content from multiple repositories or independently owned files, load `distributed-publication/SKILL.md` with `interdependent-work-graph`. Preserve exact source identities, source-local licenses and statuses, correction routing, fail-closed production retrieval, explicit fallback, and publication build provenance. - If you are designing, implementing, or reviewing agent feedback loops, closed cycles, subagent fleets (maker vs checker), orchestration in a0p/AIMMH, or any repeatable AI workflow that should run autonomously with Verify → Iterate stages, load `loop-eng/SKILL.md` and apply its 5-stage cycle, 6 building blocks, and structure-preserving closed-loop principles. From ae5203371d1cb006c96a2ae5b50fa7c49b998636 Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:49:49 -0700 Subject: [PATCH 8/9] docs(skill): expose stack-update in assistant guidance --- CLAUDE.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/CLAUDE.md b/CLAUDE.md index 52eeff3..67e2aff 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -59,6 +59,7 @@ llms/ # python -m llms.build reference runner | `meta/` | procedural | — | Meta Energy Theory axioms. Extract and preserve Energy Theory axioms from resonances among small network architectures, with formula-backed examples and overlap grids; keep Energy Theory distinct from EDCMBONE flesh/bone and FLAR implementation detail. | | `the-interdependency/` | procedural | — | Workflow protocol for The Interdependency org: code/research/GitHub maintenance, EDCMBONE transcript assembly and analysis, and mandatory usage-guidance + structure-preservation doctrine across artifacts. | | `interdependent-work-graph/` | procedural | — | Cross-repository coordination. Resolves exact participant identities, authority roles, relations, non-transfer boundaries, shared graph manifests, and validation/materialization order before selecting edit locations. Related doctrine: `the-interdependency`, `canon`. | +| `stack-update/` | procedural | — | Fail-closed structural update protocol for `The-Interdependency/stack`. Structural changes to participants, pins, authorities, relations, workspaces, BASE records, or lifecycle standing must update all affected projections, recompute the work-graph identity, and pass the deterministic stack checker as one transaction. | | `project-incubation-graduation/` | procedural | — | Lifecycle doctrine for emergent components born inside a forge/incubator. Requires qualification before extraction, provenance-preserving repository creation, explicit implementation-authority transfer, released distribution, and successful reconsumption by the former forge before graduation is complete. | | `distributed-publication/` | procedural | — | Provenance-bearing publication from distributed source owners. Preserves exact source identities, source-local licenses and statuses, correction routing, fail-closed retrieval, explicit fallback, and publication build provenance. Loads with `interdependent-work-graph`. | | `loop-eng/` | procedural | — | Loop engineering doctrine for closed feedback cycles (Discover→Plan→Execute→Verify→Iterate), maker/checker subagent separation, and autonomous verify-iterate workflows integrated with a0p/AIMMH and EDCMBONE Verify stages. | @@ -103,7 +104,7 @@ Two kinds: example; `doc-build/`, `cap-build/`, `deps-build/`, `owner-build/`, `risk-boundary-build/`, `ratios/`, `manifest/`, `llms-build/`, and `typed-meta-frontend/` define adjacent applications. `msdmd` itself is the foundation. - **Procedural skills** define an agent behaviour with no msdmd block. They state the doctrine - they enforce and the output shape they produce. `canon/`, `domain-claims/`, `visitor-intro/`, `char-compress/`, `agent-instantiation/`, `a0p-instancing/`, `plain-lens/`, `thought-lens/`, `gonol-build/`, `ucns-option-selection/`, `epac-selection-display/`, `meta/`, `the-interdependency/`, `interdependent-work-graph/`, `project-incubation-graduation/`, `loop-eng/`, `fresh-making/`, `action-calibration/`, `repo-audit-repair/`, `skill-build/`, `skill-usage/`, `ssh-automation/`, `vm-mcp/`, `sql-queries/`, `statistical-analysis/`, `explore-data/`, `validate-data/`, `data-visualization/` are the examples. + they enforce and the output shape they produce. `canon/`, `domain-claims/`, `visitor-intro/`, `char-compress/`, `agent-instantiation/`, `a0p-instancing/`, `plain-lens/`, `thought-lens/`, `gonol-build/`, `ucns-option-selection/`, `epac-selection-display/`, `meta/`, `the-interdependency/`, `interdependent-work-graph/`, `stack-update/`, `project-incubation-graduation/`, `loop-eng/`, `fresh-making/`, `action-calibration/`, `repo-audit-repair/`, `skill-build/`, `skill-usage/`, `ssh-automation/`, `vm-mcp/`, `sql-queries/`, `statistical-analysis/`, `explore-data/`, `validate-data/`, `data-visualization/` are the examples. ## msdmd block syntax @@ -253,9 +254,10 @@ There is a small stdlib Python editorial test suite. There is still no `package. 12. Before constructing, reviewing, replaying, or extending UCNS gonols, apply `gonol-build`: resolve current UCNS geometry and EDCM admissible scale options, preserve closure and atomic participation, require declared occurrence-addressed function plans, and keep incomplete constructors visible as `hmmm`. 13. Before selecting among UCNS options, apply `ucns-option-selection`: freeze the scoped decision boundary, enforce noncompensable eligibility and evidence gates, require explicit ratification, and preserve non-transfer, rollback, negative evidence, and `hmmm`. 14. Before selecting and displaying an EPAC artifact, apply `epac-selection-display`: pin the provisional source, exact target, receipt, and available renderer; preserve status, nonclaims, sealed comparison, and `hmmm`; and keep WebMCP read-only. -15. For LLM instructions, edit `LLMS` source blocks and regenerate `llms.txt` with `python -m llms.build --root . --out llms.txt --apply`. -16. For SSH automation and large terminal pastes containing SSH, apply `ssh-automation`: verify endpoint identity and host trust, preserve local and remote interpreter boundaries, make retries and rollback explicit, and contain option/trap/exit effects inside a child shell. -17. When an emergent component is incubated inside a forge and may become independently authoritative, apply `project-incubation-graduation`: qualify it before extraction, preserve provenance, publish from the new authority, require downstream reconsumption, then sever the incubated implementation path before declaring graduation. +15. Before mutating `The-Interdependency/stack` structure, apply `stack-update` with `interdependent-work-graph`; update every affected authority/provenance projection, remove superseded claims, recompute the work-graph digest, and require the deterministic stack checker before merge. +16. For LLM instructions, edit `LLMS` source blocks and regenerate `llms.txt` with `python -m llms.build --root . --out llms.txt --apply`. +17. For SSH automation and large terminal pastes containing SSH, apply `ssh-automation`: verify endpoint identity and host trust, preserve local and remote interpreter boundaries, make retries and rollback explicit, and contain option/trap/exit effects inside a child shell. +18. When an emergent component is incubated inside a forge and may become independently authoritative, apply `project-incubation-graduation`: qualify it before extraction, preserve provenance, publish from the new authority, require downstream reconsumption, then sever the incubated implementation path before declaring graduation. ## hmmm From 00a73470126b04610d1fa0a0a6bc0c6d6918498c Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Fri, 11 Sep 2026 23:56:14 -0700 Subject: [PATCH 9/9] fix(skill): restore visitor-intro index identity --- skills.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills.json b/skills.json index 2adf736..12931d6 100644 --- a/skills.json +++ b/skills.json @@ -24,7 +24,7 @@ {"name":"manifest","path":"manifest/SKILL.md","kind":"metadata-block","depends_on":["msdmd"],"description":"Living-spec generator. Derives the mechanical, observable facts of a repo (package name, version, description, license, authors, repository, build backend, development status, supported Python versions, keywords, runtime dependencies, optional extras, top-level layout, CI workflows) from pyproject.toml + the file tree and splices them into a machine-owned, marked block inside CLAUDE.md — keeping the doc from silently drifting from the code. Ships a stdlib-only generator with --write (refresh), --check (CI drift gate), and --print modes. Load this when: setting up or maintaining a CLAUDE.md / AGENTS.md so its factual half is generated rather than hand-typed; wiring a CI check that fails when docs drift from pyproject/version/deps/layout; deciding which parts of a doc to generate vs. hand-author; or onboarding a new org repo to the living-spec convention."}, {"name":"llms-build","path":"llms-build/SKILL.md","kind":"metadata-block","depends_on":["msdmd"],"description":"Self-declaring LLM instructions file (llms.txt) built on msdmd. Modules or central files declare LLMS blocks with project overview, key definitions, architecture summary, and agent usage rules. A runner aggregates them into a standardized root llms.txt and surfaces drift/gaps. Load this when creating, updating, or maintaining llms.txt for any repo consumed by LLMs or agents."}, {"name":"char-compress","path":"char-compress/SKILL.md","kind":"procedural","description":"Character-based context compression for agent handoff and skill writing, owned as a skill-lib procedure rather than current UCNS mathematics. Use this when compressing a long thread, document, repo audit, canon handoff, or agent working-memory state; when a context window is filling and operative facts must survive; when writing a SKILL.md that should be flesh-dense and bone-sparse; or when checking whether a compression deleted negation, order, quantifier, operator, named object, value, decision, or unresolved hmmm. Historical bone/flesh and text-stack terminology is local compression notation, not a UCNS theorem/status transfer, EDCM constructor, or edcmbone metric implementation."}, - {"name":"visitor-intro","path":"visitor-intro/SKILL.md","kind":"procedural","description":"Onboarding tour for visitors arriving at any The-Interdependency repo. Load this when an unfamiliar user asks \"what is this?\", \"what is The Interdependency?\", \"how do these repos fit together?\", \"where do I start?\", or otherwise signals they are new to the org. Gives the agent a consistent, repo-aware way to orient a newcomer without inventing org-level facts."}, + {"name":"visitor-intro","path":"visitor-intro/SKILL.md","kind":"procedural","description":"Onboarding tour for visitors arriving at any The-Interdependency repo. Load this when an unfamiliar user asks \"what is this?\", \"what is The Interdependency?\", \"how do these repos fit together?\", \"where do I start?\", or otherwise signals they are new to the org. Gives the agent a consistent, repo-aware way to orient a newcomer without inventing facts."}, {"name":"agent-instantiation","path":"agent-instantiation/SKILL.md","kind":"procedural","description":"Methodology for instantiating, forking, running, merging, and retiring agents in the a0 platform and its near-identical mirror a0ucns. Load this when adding or changing a sub-agent spawn path, a PCNA instance fork/merge, an agent definition or naming scheme, spawn caps or approval gating, an agent run/log table, a heartbeat-driven agent task, or a checkpoint of agent state. Use it before writing any code that creates, addresses, schedules, or tears down an agent or sub-agent, so the new code follows the platform's existing lifecycle, fork/merge, identity, and gating contracts rather than inventing a parallel one. NOTE: a0-betatest (a0p) has diverged to a different per-user CRUD + native-ZFAE instancing model — this skill's spawn/fork/merge sequence does NOT apply there; see \"a0-betatest divergence\"."}, {"name":"a0p-instancing","path":"a0p-instancing/SKILL.md","kind":"procedural","description":"Methodology for instancing agents in a0-betatest (the a0p research instrument), whose model diverges from canonical a0. Load this when adding or changing an AgentInstance / CharacterSheet CRUD path, a per-instance native ZFAE weight bank or its training/distillation loop, a ZFAE inference mode, a sentinel evaluation or pending-override gate, a per-agent safetensors checkpoint, or volatile sub-context memory — anywhere under a0-betatest `backend/`. Use it before writing code that creates, addresses, trains, runs, governs, or persists an a0p agent, so the code follows a0p's per-user CRUD + native-ZFAE + sentinel model instead of a0's spawn/fork/merge model. For canonical a0 and its mirror a0ucns, use `agent-instantiation` instead — a0p does NOT have `sub_agent_spawn`, a spawn executor, or `InstanceMerge`."}, {"name":"plain-lens","path":"plain-lens/SKILL.md","kind":"procedural","description":"Building a plain-language, multi-lens companion view of dense canonical text — an easier on-ramp that does not replace or talk down to the source. Load this when you are asked to make an informationally dense document (canon, spec, articles, legal/normative text) easier to approach for newcomers; when building an \"explain it through the lens of X\" selector (domain, audience, or role); when designing progressive-disclosure or layered ELI-not-stupid reading UX; when a dynamic, data-driven site must keep its existing static page as a graceful fallback; or when you need an EDCM-style two-speaker tension reading between a body text and its footnotes/caveats. Use this when the risk is either drowning readers in density or insulting them with oversimplification."},