legrab · legrab · Aug 10, 2026 · Aug 10, 2026
@@ -26,6 +26,11 @@ Architectural simplification of the `full` profile: reduced meta-ceremony while
 - Deduplicated the external-source provenance field list between `learning-closure` and `learning-freshness`; `learning-closure` is now the single owner.
 - `full/learning-flow/README.md` diagram and "Understanding and assessment" section updated to match the reduced skill count and single canonical rule.
 - `ticket-learning-path`'s implementation-handoff step now names `repository-learning` instead of the three merged skills.
+- Consolidated `repository-learning` into one common skill owner shared by minimal and full profiles, preserving focused Orientation, Bug, Feature, and Refactor routes.
+- Reduced profile `learning-flow/AGENTS.md` files to routing and profile-specific persistence concerns, removing duplicated common policy.
+- Removed redundant full-profile bootstrap, playbook, and understanding-check documents whose rules are now owned by the common workflow or selected skill.
+- Added regression coverage for shared skill ownership and profile routing.
+
 
 ## 1.1.0
 

@@ -1,14 +1,14 @@
 .gitattributes	40
 .gitignore	324
 AGENTS.md	2995
-CHANGELOG.md	24247
+CHANGELOG.md	24788
 LICENSE	2213
 README.md	8952
 adoption/ADOPT.md	4177
 adoption/README.md	2057
-docs/AGENTIC_WORKFLOW_SANITY.md	9207
+docs/AGENTIC_WORKFLOW_SANITY.md	9802
 docs/ARCHITECTURE.md	7131
-docs/DESIGN_NOTES.md	35837
+docs/DESIGN_NOTES.md	36475
 docs/EDUCATION_MODEL.md	5452
 docs/INITIALIZE_LEARNING_FLOW.md	10880
 docs/README.md	4016
@@ -19,12 +19,13 @@ docs/references/REFERENCE_REVIEW_GOOSE.md	2486
 docs/references/REFERENCE_REVIEW_LEARNING_FLOW_ADJUSTMENT.md	9505
 docs/references/REFERENCE_REVIEW_LITT.md	2069
 docs/references/REFERENCE_REVIEW_POCOK.md	2155
-sample/README.md	2997
+sample/README.md	3065
 sample/common/.agents/skills/agentic-workflow/SKILL.md	2686
 sample/common/.agents/skills/learn-anything/SKILL.md	1756
 sample/common/.agents/skills/learn-anything/agents/openai.yaml	246
 sample/common/.agents/skills/learning-closure/SKILL.md	3605
 sample/common/.agents/skills/learning-freshness/SKILL.md	1908
+sample/common/.agents/skills/repository-learning/SKILL.md	4904
 sample/common/.agents/skills/structured-change/SKILL.md	3059
 sample/common/.agents/skills/structured-change/knowledge/engineering/ai-collaboration.md	2533
 sample/common/.agents/skills/structured-change/knowledge/engineering/architecture.md	1386
@@ -37,7 +38,7 @@ sample/common/.agents/skills/structured-change/templates/design.md	649
 sample/common/.agents/skills/structured-change/templates/exploration.md	368
 sample/common/.agents/skills/structured-change/templates/structure.md	243
 sample/common/agentic-flow/.managed-files	170
-sample/common/agentic-flow/.managed-skills	86
+sample/common/agentic-flow/.managed-skills	106
 sample/common/agentic-flow/.template-version	6
 sample/common/agentic-flow/AGENTS.md	5995
 sample/common/agentic-flow/CONFIGURE.md	4475
@@ -74,34 +75,33 @@ sample/profiles/full/.agents/skills/learning-bootstrap/SKILL.md	1491
 sample/profiles/full/.agents/skills/ticket-learning-path/SKILL.md	1513
 sample/profiles/full/.agents/skills/ticket-learning-path/templates/ticket-learning-path.md	405
 sample/profiles/full/learning-flow/.managed-files	87
-sample/profiles/full/learning-flow/.managed-skills	77
+sample/profiles/full/learning-flow/.managed-skills	57
 sample/profiles/full/learning-flow/.template-profile	5
 sample/profiles/full/learning-flow/.template-version	6
-sample/profiles/full/learning-flow/AGENTS.md	6548
+sample/profiles/full/learning-flow/AGENTS.md	2580
 sample/profiles/full/learning-flow/MAP.md	1464
-sample/profiles/full/learning-flow/README.md	2320
+sample/profiles/full/learning-flow/README.md	2345
 sample/profiles/full/learning-flow/REPOSITORIES.md	439
 sample/profiles/full/learning-flow/TAKEAWAYS.md	970
-sample/profiles/minimal/.agents/skills/repository-learning/SKILL.md	3718
 sample/profiles/minimal/learning-flow/.managed-files	87
-sample/profiles/minimal/learning-flow/.managed-skills	20
+sample/profiles/minimal/learning-flow/.managed-skills	0
 sample/profiles/minimal/learning-flow/.template-profile	8
 sample/profiles/minimal/learning-flow/.template-version	6
-sample/profiles/minimal/learning-flow/AGENTS.md	2633
+sample/profiles/minimal/learning-flow/AGENTS.md	1362
 sample/profiles/minimal/learning-flow/MAP.md	1229
 sample/profiles/minimal/learning-flow/README.md	1974
 sample/profiles/minimal/learning-flow/TAKEAWAYS.md	973
 sample/root/AGENTS.md	2102
 sample/root/AGENTS.pointer.md	551
 scripts/README.md	6771
 scripts/install.bat	1477
-scripts/install.ps1	40236
-scripts/install.sh	34910
+scripts/install.ps1	40477
+scripts/install.sh	34980
 skill-evals/README.md	1667
 skill-evals/adoption-cases.yaml	1337
 skill-evals/agentic-cases.yaml	8895
 skill-evals/conversation-cases.yaml	3653
-skill-evals/full-cases.yaml	4648
-skill-evals/learning-lifecycle-cases.yaml	1599
-skill-evals/minimal-cases.yaml	3655
+skill-evals/full-cases.yaml	5001
+skill-evals/minimal-cases.yaml	3913
 skill-evals/structured-change-cases.yaml	4710
+skill-evals/learning-lifecycle-cases.yaml	1599
@@ -213,3 +213,17 @@ For each scenario, review the agent interaction for:
 - unnecessary framework terminology in the user-facing result.
 
 A change to the common workflow or a broadly loaded skill should rerun the affected scenarios. A change to a narrow task skill only needs the scenarios that can route to that skill plus the ordinary-task checks needed to ensure it does not become ambient.
+
+### 12. Shared skill ownership
+
+**Prompt:** Update the repository-learning behavior used by both minimal and full profiles.
+
+Expected behavior:
+
+- identify `repository-learning` as one shared skill owner;
+- do not create or edit profile-specific duplicate implementations;
+- ensure profile managed-skill declarations and `MANIFEST.txt` resolve to the same source;
+- preserve profile-specific routing in `learning-flow/AGENTS.md`.
+
+Failure signal: a profile declares a skill whose implementation is only discoverable by following another profile, or two profile copies can drift independently.
+
@@ -4,6 +4,15 @@
 
 The harness should keep a developer able to reason about a repository while collaborating with an agent, and let any learner use the same lightweight methods for a general subject. It should improve delivery, code and architecture understanding, domain reasoning, debugging, ownership growth, and conversational learning without making workflow administration or learning administration the primary activity.
 
+## v1.3 consolidation and ownership boundaries
+
+The 1.3 cleanup makes three small maintenance boundaries explicit:
+
+1. `repository-learning` has one common skill owner. Minimal and full profiles differ in routing and persistence surfaces, not by carrying duplicate implementations.
+2. Profile `learning-flow/AGENTS.md` files are routing contracts. Common collaboration, context economy, evidence, understanding-check, and handoff policy remains owned by the common agentic/education layer.
+
+The goal is lower effective context, less opportunity for agentic drift, and faster human navigation without introducing another framework layer.
+
 ## Current three-layer architecture
 
 The current architecture consolidates the earlier ownership distinctions into three user-facing framework layers:

@@ -24,6 +24,7 @@ sample/common/agentic-flow/
 sample/common/.agents/skills/agentic-workflow/
 sample/common/.agents/skills/learn-anything/
 sample/common/.agents/skills/structured-change/
+sample/common/.agents/skills/repository-learning/
 sample/common/local/learning-history.md
 sample/profiles/minimal/
 sample/profiles/full/
@@ -35,7 +36,7 @@ sample/root/
 |---|---|
 | `agentic-flow/` | planning, autonomy, validation, records, and handoff |
 | `agentic-flow/EDUCATION.md` | system ownership, resilience, AI independence, and teaching judgment |
-| `learning-flow/` | repository education and durable shared knowledge |
+| `learning-flow/` | repository education, profile routing, and durable shared knowledge |
 | `learn-anything` | conversational learning without repository inspection |
 | `structured-change` | Explore/Design/Approve sequencing for one consequential change, any profile |
 | `extensions/regulatory` | optional, additive traceability/validation/risk-management knowledge |

@@ -0,0 +1,79 @@
+---
+name: repository-learning
+description: Understand or work on a repository through one focused route for orientation, bugs, analogous features, or safe refactors. Use when repository understanding materially affects the task; do not turn mechanical work into a learning workflow.
+---
+
+# Repository learning
+
+Follow `agentic-flow/AGENTS.md` and `agentic-flow/SETTINGS.md`. Read `agentic-flow/EDUCATION.md` selectively and only the relevant shared records.
+
+## Shared route
+
+1. Identify the real outcome, system boundary, governing rule or invariant, representative path, and proof surface.
+2. Work from decisive repository evidence before committing to a model or proposed design.
+3. Use the smallest responsible investigation, attempt, or change.
+4. Verify against decisive evidence and relevant failure modes.
+5. Use at most one consequential understanding check when a mistaken model would affect later reasoning.
+6. Transfer only verified, reusable learning into the normal handoff or a qualified shared record.
+
+Select exactly one branch below. Do not load or execute the other branches.
+
+## Orientation
+
+1. Identify the intended human, business, scientific, or physical outcome.
+2. Frame actor or caller, capability, governing rule, and system boundary.
+3. Show a compact domain slice before file detail.
+4. Trace one representative execution, data, material, or decision path.
+5. Connect claims to source, tests, configuration, runtime or domain evidence, or explicit inference.
+6. Identify important failure, access, deployment, legacy, or human-control boundaries when relevant.
+7. Name the highest-value unknown.
+8. Stop when the user can locate, explain, challenge, and safely continue.
+
+Output a compact mental model, useful visual when appropriate, representative path, evidence, uncertainty, control boundary, and one next challenge.
+
+## Bug
+
+1. State the affected real-world outcome or rule, observable symptom, and falsifiable expectation.
+2. Identify immediate safety, data, access, or operational containment when relevant.
+3. Find the smallest discriminating reproduction, test, trace, log, or safe observation.
+4. Rank credible hypotheses and test one uncertainty at a time.
+5. Explain the failure mechanism before changing code.
+6. Validate machine-generated and human hypotheses against decisive evidence.
+7. Apply the narrowest responsible containment or fix when requested.
+8. Add proportional regression evidence and name the degraded mode, fallback, or untested boundary.
+9. Stop when one mechanism explains the symptom and evidence distinguishes it from credible alternatives.
+
+Do not keep a hypothesis diary. Report symptom, expectation, containment, decisive evidence, mechanism, fix or seam, regression proof, operational boundary, and remaining risk.
+
+## Feature
+
+1. Define the actor, intended outcome, capability, observable behavior, and governing invariants.
+2. Test whether the behavior should be built or automated, and what must remain a human decision.
+3. Search by behavior and evidence, not name alone.
+4. Compare candidates across domain rules, data flow, configuration, interface, tests, failure effects, access, and operations.
+5. Select the nearest valid analogue.
+6. Separate shared invariants from intentional differences.
+7. Use the smallest established extension seam.
+8. Prove the reused invariant, intended difference, failure behavior, and control boundary in proportion to risk.
+
+Ask at most one check about why the analogue is valid or where copying it would be wrong. Report the selected analogue, invariant/difference boundary, build judgment, seam, proof, risks, controls, and deferred divergence.
+
+## Refactor
+
+1. State the behavior or domain invariant that must remain stable.
+2. Identify the observable contract, failure boundary, access or deployment control, and fallback that cannot be lost.
+3. Inspect existing proof and add characterization only where necessary.
+4. Identify the smallest safe seam.
+5. Apply reviewable transformations.
+6. Run the narrowest useful checks after meaningful steps.
+7. Confirm the result is simpler to own, validate, recover, and explain.
+8. Confirm no custom glue or AI dependency was added unnecessarily.
+9. Stop when the contract is explicit, relevant checks pass, and no unproven boundary is hidden.
+
+Ask at most one check about the preserved contract, failure boundary, or new responsibility boundary. Report the contract, evidence before and after, transformation sequence, resilience preserved, simplification, and remaining risk.
+
+## Persistence
+
+Use `MAP.md`, `TAKEAWAYS.md`, and, in the full profile, `REPOSITORIES.md` as the single owners for durable shared knowledge. Keep private attempts, personal state, uncertainty, secrets, and sensitive operational evidence under `.local/`.
+
+Promote only verified, repository-specific, reusable, non-sensitive findings that are costly enough to rediscover.
@@ -3,3 +3,4 @@ learn-anything
 structured-change
 learning-closure
 learning-freshness
+repository-learning
@@ -1,4 +1,3 @@
 learning-bootstrap
-repository-learning
 change-explainer
 ticket-learning-path