Skip to content
3 changes: 2 additions & 1 deletion AGENTS.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ the skill. Treat it as the public contract.
`ratios`, `manifest`, `llms-build`, and `typed-meta-frontend`) define metadata blocks that other
modules declare inside their own source files. Other skills (currently
`canon`, `domain-claims`, `char-compress`, `visitor-intro`, `agent-instantiation`,
`a0p-instancing`, `plain-lens`, `gonal-morphology`, `meta`, `the-interdependency`, `loop-eng`, and `skill-build`) are procedural and
`a0p-instancing`, `plain-lens`, `gonal-morphology`, `meta`, `the-interdependency`, `interdependent-work-graph`, `loop-eng`, and `skill-build`) are procedural and
define no block.

A machine-readable index is also available at `skills.json` if you
Expand Down Expand Up @@ -105,6 +105,7 @@ propagate from here.
page that must keep a static fallback — load `plain-lens/SKILL.md`; keep the
paraphrase subordinate to the canon and mark uncertain mappings as `hmmm`.
- 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 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.
- If you are creating a new skill, revising an existing skill, bringing skills into compliance, or designing a skill-specific test suite, load `skill-build/SKILL.md` and answer its trigger, source-of-truth, workflow, validation, and `hmmm` question sets before patching.

Expand Down
3 changes: 2 additions & 1 deletion CLAUDE.md
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@ llms/ # python -m llms.build reference runner
| `gonal-morphology/` | procedural | — | Three-core gonal morphology canon. omega=bones (closed-class+affixes, weight 0.8), phi=roots (open-class, 0.4), psi=words=`phi⊠omega` (1.0); leaf=157 chars, seed=phrase/clause (equivalent under LCM). One operator ⊠ = UCNS `multiplyFuel` at every depth — reuse, don't reimplement. Recomposition runs; decomposition domain-confirmed (`AlignedComplete`) but proof-pending (no theorem-status transfer). |
| `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`. |
| `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. |
| `skill-build/` | procedural | — | Skill authoring and compliance workflow. Provides the required question set for creating/revising skills, choosing metadata-block vs procedural shape, designing individualized skill test suites, and bringing existing skills into compliance. |

Expand Down Expand Up @@ -88,7 +89,7 @@ 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/`, `gonal-morphology/`, `meta/`, `the-interdependency/`, `loop-eng/`, and `skill-build/` are the examples.
they enforce and the output shape they produce. `canon/`, `domain-claims/`, `visitor-intro/`, `char-compress/`, `agent-instantiation/`, `a0p-instancing/`, `plain-lens/`, `gonal-morphology/`, `meta/`, `the-interdependency/`, `interdependent-work-graph/`, `loop-eng/`, and `skill-build/` are the examples.

## msdmd block syntax

Expand Down
9 changes: 9 additions & 0 deletions ORG_DISTRIBUTION.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ Propagation PRs should cite this repository and the source commit SHA.
* `meta/` — Meta Energy Theory Axioms canon skill
* `gonal-morphology/` — three-core gonal morphology canon (omega/phi/psi; ⊠ = UCNS carrier-LCM)
* `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
* `loop-eng/` — closed-loop engineering doctrine for repeatable Discover→Plan→Execute→Verify→Iterate workflows
* `skill-build/` — skill authoring, compliance, and individualized test-suite question workflow

Expand Down Expand Up @@ -101,6 +102,14 @@ trees, and vendored `.agents/skills/` copies should not pollute the denominator.

## Rule

Before assigning a stack-level task to one repository, agents should read:

```text
.agents/skills/interdependent-work-graph/SKILL.md
```

Resolve the exact participating repository and evidence-source identities first. Repository boundaries remain authority and provenance boundaries, not agent-attention boundaries.

Before creating a new module, route, service, adapter, schema, worker,
engine, UI panel, migration, or experiment, agents should read:

Expand Down
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ into [`llms.txt`](llms.txt) from self-declared `LLMS` blocks.
| [`meta/`](meta/SKILL.md) | Meta Energy Theory Axioms. Extracts and preserves Energy Theory axioms from resonances among small network architectures, with formula-backed examples and overlap grids; keeps Energy Theory distinct from EDCMBONE flesh/bone and FLAR implementation detail. Independent of msdmd. |
| [`gonal-morphology/`](gonal-morphology/SKILL.md) | Canonical three-core gonal morphology: text as UCNS objects across a char→root/bone/word→phrase/clause ladder under one carrier-LCM operator (⊠ = UCNS `multiplyFuel`). omega=bones, phi=roots, psi=words=`phi⊠omega`; adj/adv are flesh. Reuse the UCNS operator. Recomposition runs; decomposition is domain-confirmed (`AlignedComplete`) but proof-pending. 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. |
| [`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. |
| [`skill-build/`](skill-build/SKILL.md) | Skill authoring and compliance workflow. Guides agents through the question set for creating or revising skills, choosing metadata-block vs procedural shape, designing individualized test suites, and bringing existing skills into a shared compliance pattern. Independent of msdmd. |

Expand Down Expand Up @@ -132,7 +133,7 @@ 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`, `gonal-morphology`, `meta`, `the-interdependency`, `loop-eng`, and `skill-build` are the existing examples). To add one:
`a0p-instancing`, `plain-lens`, `gonal-morphology`, `meta`, `the-interdependency`, `interdependent-work-graph`, `loop-eng`, and `skill-build` are the existing examples). To add one:

1. Define when the skill loads (the `description` field in the YAML
frontmatter is what your harness will read).
Expand Down
4 changes: 2 additions & 2 deletions domain-claims/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -137,8 +137,8 @@ or repository proximity.
## Workflow

1. **Detect promotion.** Determine whether the word will control canon, structure,
theorem language, implementation, measurement, or encoding. If not, stop; ordinary
language remains fluid.
theorem language, implementation, measurement, or encoding. If not, stop;
ordinary language remains fluid.
2. **Enumerate candidate domains.** Name every domain whose claim could reasonably
apply in the current scope.
3. **Declare the claim.** Create or retrieve the domain-claim record before drafting
Expand Down
170 changes: 170 additions & 0 deletions interdependent-work-graph/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,170 @@
---
name: interdependent-work-graph
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.
---

# interdependent-work-graph — coordinate the problem, not the folder

Use this procedural skill when the real work graph crosses repository boundaries. Repository boundaries preserve authority, provenance, permissions, and release history. They do not define the limit of one agent's attention.

## Core contract

```text
repository boundary != agent boundary
repository boundary == authority and provenance boundary
```

- Resolve the complete participating graph before choosing where to edit.
- Record exact commits, not only branch names or package availability.
- State what authority each repository or evidence source owns.
- Let one agent coordinate the graph, or let several agents consume the same deterministic graph record.
- Transfer no semantic authority, theorem status, certification status, measurement validity, or empirical status merely because repositories are connected.
- Preserve unresolved mappings and authentication questions as `hmmm`.

## Non-trigger

Do not load this skill merely because a repository has ordinary runtime dependencies. A self-contained patch whose correctness, authority, and validation all remain inside one repository does not require a shared work graph.

Load it when crossing a boundary changes what must be known, preserved, validated, published, or refused.

## Authority model

A participant declares an authority role and a work relation. Common examples:

```text
METAPAT semantic authority
UCNS mathematical representation and its own proof/status evidence
EDCM measurement, projection, and result contracts
skill-lib reusable build and evidence discipline
corpus bounded external source evidence
website publication and presentation consumer
```

These are examples, not a universal fixed list. Read the participating repositories before assigning roles.

## Workflow

1. **Discover the graph.** Identify every repository, package, corpus, schema, workflow, or publication surface whose exact state can change the answer.
2. **Resolve identity.** Pin an exact commit, immutable artifact digest, versioned schema, or explicit `hmmm` for each participant. Moving branch names are navigation aids, not evidence identities.
3. **Assign authority.** State what each participant may define and what it merely consumes.
4. **Declare relations.** Record producer, consumer, evidence source, build-doctrine source, publication target, compatibility peer, or other precise relation.
5. **Declare non-transfer boundaries.** At minimum consider authority, proof status, certification, measurement validity, empirical validity, and user-data permissions.
6. **Choose edit locations.** Patch each claim at its owning source. Do not repair a producer defect by shadowing its schema in a consumer.
7. **Coordinate execution.** Prefer one shared identity record, fixture, or manifest that all agents and workflows consume over separate repo-local reconstructions.
8. **Validate the graph.** Run repository-local gates plus at least one cross-repository fixture or identity check proving that the connected surfaces remain distinct and compatible.
9. **Publish bounded results.** Each PR describes its local changes and cites the shared graph identity. Do not merge dependent consumers before required producers are available.
10. **Carry hmmm forward.** Unknown semantic mappings, signatures, release ordering, or governance choices remain explicit boundary objects.

## Stack-manifest reference contract

The first executable reference shape is:

```json
{
"schema": "the-interdependency.stack-manifest",
"version": "1.0.0",
"work_graph_sha256": "<sha256>",
"repositories": [
{
"repository": "owner/name",
"commit": "<40-hex commit>",
Comment on lines +67 to +70

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Support non-repository participants in manifests

For stack-level runs where a corpus, package, schema, workflow, or publication surface changes the answer, this reference manifest can only encode Git repositories with 40-hex commits. Those participants either have to be omitted from the hashed graph identity or mis-modeled as repositories, so later agents cannot reproduce the complete graph for non-repo evidence sources; add typed participants with digest/version/schema fields or parallel artifact/schema sections before this becomes the machine contract.

Useful? React with 👍 / 👎.

"authority": "what this participant may define",
"relation": "how it participates in this work"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Encode work relations as graph edges

When a manifest has multiple producers or consumers, this per-participant relation text cannot identify which participant depends on which other participant, so two different work graphs can share the same participants and boundaries while still getting the same work_graph_sha256. That undermines the validation and materialization order the skill requires; include a hashed edge list such as from, to, and relation_type for producer, consumer, schema, or corpus links.

Useful? React with 👍 / 👎.

}
],
"boundaries": {
"authority_transfer": false,
"proof_status_transfer": false,
"measurement_status_transfer": false,
"semantic_mapping": "external-provenance|declared mapping|hmmm",
Comment thread
erinepshovel-code marked this conversation as resolved.
"agent_scope": "cross-repository-work-graph",
"hmmm": []
}
}
```

The digest is SHA-256 over canonical JSON containing exactly `repositories` and `boundaries`, sorted by key with compact separators. In version 1.0.0 the order of the `repositories` array is itself part of the hashed identity: an emitter lists participants in a declared, stable order, and the same participants in a different order produce a different digest. Key sorting does not reorder arrays, so two agents rebuilding the same graph must consume the emitter's declared order rather than re-discovering it. Consuming implementations may add versioned fields only through an explicit schema revision.

The 1.0.0 `boundaries` block is the minimal machine-carried set. Certification-status and empirical-validity non-transfer are binding obligations of this skill (workflow step 5) even where a 1.0.0 manifest carries no explicit fields for them; explicit `certification_status_transfer` and `empirical_status_transfer` fields arrive through the next schema revision, not through ad-hoc emitter extensions. Non-repository participants (corpus, package, schema, workflow, or publication surfaces) are encoded in 1.0.0 as `repositories` entries whose `authority` and `relation` describe the evidence source; typed participant records are likewise deferred to a schema revision.

A manifest is identity and coordination evidence. It is not cryptographic producer authentication unless a separate signature contract exists.

## Workflow separation

For expensive or generated cross-repository work:

- Pull requests validate read-only whenever possible.
- Materialization is an explicit operation with narrow write permission and a named non-default target branch.
- Generated evidence is sealed once and reused by later agents or workflows rather than independently reconstructed.
- A write-back workflow must not patch source code immediately before claiming to validate that source.
- Repository-specific artifacts include the shared graph identity when their interpretation depends on the graph.

## Output shape

When this skill is active, produce or maintain:

```markdown
## Work graph
- participant: exact identity — authority — relation

## Edit ownership
- repository/path: change and why it belongs there

## Cross-repository boundaries
- no-transfer statements
- permission boundaries
- hmmm

## Validation
- local gates
- shared fixture or manifest check
- release/materialization order
```

For machine-consumed work, also emit the versioned stack manifest or an explicitly named equivalent.

## Validation

A successful application demonstrates:

- every participant has an exact or visibly unresolved identity;
- every participant has one stated authority role and work relation;
- no consumer shadows a producer-owned schema or algebra;
- no theorem, semantic, certification, measurement, or empirical status transfers silently;
- the work-graph digest recomputes deterministically;
- repository-local tests pass;
- at least one cross-repository fixture, import, adapter, artifact, or workflow proves the connected path;
- later agents can resume from the graph record without guessing which commits were used.

## Anti-patterns

- Assigning one AI to one repository when the task's truth conditions span several.
- Treating the currently open repository as the source of every term it imports.
- Installing “latest” dependencies during evidence-producing runs.
- Reimplementing a producer schema or algebra inside a consumer.
- Letting several agents rebuild incompatible local versions of the same evidence.
- Using a digest as though it were a signature.
- Hiding unresolved mappings behind constructor defaults.
- Allowing validation workflows to mutate the source they are validating.

## Minimal example

A corpus-to-measurement run may bind:

```text
corpus commit evidence source
skill-lib commit build/evidence doctrine
METAPAT commit semantic authority
UCNS commit mathematical producer
EDCM commit measurement/artifact producer
```

One agent can follow the complete path. Separate agents can work on different participants if each consumes the same manifest and respects edit ownership.

## hmmm

- The organization-wide persistent service or user interface for live work graphs is not yet selected.
- Content identities do not yet provide cryptographic producer or transport authentication.
- Whether the stack-manifest schema remains a procedural-skill reference contract or later becomes its own metadata-block/schema skill.
- The next stack-manifest schema revision is expected to add explicit `certification_status_transfer` and `empirical_status_transfer` boundary fields, a canonical `repositories` ordering (for example by `repository` then `commit`) in place of declared-order identity, typed non-repository participants with digest/version/schema identities, and an explicit hashed edge list (`from`, `to`, `relation_type`) so distinct work graphs over the same participants cannot share one digest. Version 1.0.0 stays as sealed by the EDCM OEWN 2025 run.
- Cross-repository merge orchestration remains repository-host dependent; the skill defines order and evidence, not a universal transaction mechanism.
Loading
Loading