neo-agent-skills 0.1.0 → 0.1.3

package/.agents/skills/create-skill/SKILL.md

@@ -5,4 +5,4 @@ description: "Authoritative guide on how to architect, format, and structure new
 # Skill Creation Framework
 If you are tasked with creating a new Agent Skill, you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/create-skill/references/skill-authoring-guide.md` before creating any files. This prevents system prompt bloat and ensures future agents can parse your skill correctly.
 
-**Source of Authority:** [ADR 0008: SKILL.md Anatomy and Authoring Contract](../../../learn/agentos/decisions/0008-skill-anatomy-and-authoring-contract.md) — the graph-queryable canonical decision substrate for skill-shape (frontmatter contract, Map/Atlas split, manifest contract, anti-patterns). This skill's `references/skill-authoring-guide.md` is the procedural HOW-TO companion.
+**Source of Authority:** [ADR 0008: SKILL.md Anatomy and Authoring Contract](https://github.com/neomjs/neo/blob/dev/learn/agentos/decisions/0008-skill-anatomy-and-authoring-contract.md) — the graph-queryable canonical decision substrate for skill-shape (frontmatter contract, Map/Atlas split, manifest contract, anti-patterns). This skill's `references/skill-authoring-guide.md` is the procedural HOW-TO companion.

package/.agents/skills/create-skill/references/skill-authoring-guide.md

@@ -68,7 +68,7 @@ The canonical worked example is `AGENTS.md` `Compaction Taxonomy` — every row
 
 ### Byte Budget for SKILL.md Routers
 
-Empirical floor for the `SKILL.md` router itself: **7-12 lines** (range across all 18 current skills, anchored in `learn/agentos/measurements/cognitive-load-baseline-2026-05.md` §7 *SKILL.md Router Byte-Budget Baseline*; routers exceeding 12 lines historically benefit from extracting content into payload).
+Empirical floor for the `SKILL.md` router itself: **7-12 lines** (range across all 18 current skills, anchored in the Brain-owned [cognitive-load baseline](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/measurements/cognitive-load-baseline-2026-05.md) §7 *SKILL.md Router Byte-Budget Baseline*; routers exceeding 12 lines historically benefit from extracting content into payload).
 
 This is a *discriminator*, not a hard cap. A 14-line router can be justified if the additional lines are load-bearing trigger-language; an 8-line router lacking load-bearing trigger-language can be over-engineered. Use the 7-12 line floor as the *prompt* for "should this content live here, or in payload?"
 
@@ -185,7 +185,7 @@ Before pushing your new skill, check:
 
 Any PR that **creates OR modifies** `.agents/skills/**` substrate is an **agent-consumed governance-surface** change. Beyond the skill-shape checks above, the `pr-review` Contract-Completeness + load-effect audits require **two PR-open gates** — author both **up-front** (each is documentation-only: no diff, head, or CI impact):
 
-1. **Contract Ledger on the SOURCE TICKET** — not just the PR body. Post the T3 matrix (`learn/agentos/process/contract-ledger.md`) as a comment on the ticket / epic; the Contract-Completeness audit checks the *originating ticket*, so a PR-body-only ledger does not satisfy it.
+1. **Contract Ledger on the SOURCE TICKET** — not just the PR body. Post the T3 matrix defined by the Brain-owned [contract-ledger protocol](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/contract-ledger.md) as a comment on the ticket / epic; the Contract-Completeness audit checks the *originating ticket*, so a PR-body-only ledger does not satisfy it.
 2. **`/turn-memory-pre-flight` load-effect audit in the PR body** — document the load-runtime-effect placement: which file is the always-loaded **Map** (SKILL.md router / hot workflow §) vs the conditional **World-Atlas** payload, and that the net always-loaded delta is minimal or negative (rule bodies belong in the conditional audit, never the always-loaded Map).
 
 Doing both up-front avoids the predictable single-cycle `CHANGES_REQUESTED` this gate otherwise fires.

package/.agents/skills/document-references.v1.json

@@ -0,0 +1,285 @@
+{
+    "schemaVersion": "document-references.v1",
+    "selector": "learn/[A-Za-z0-9_./-]+\\.md",
+    "rows": [
+        {
+            "token": "learn/agentos/AGENTS_ATLAS.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/agentos/AGENTS_ATLAS.md",
+            "referencingSkills": [
+                "neo-identity-update",
+                "pull-request",
+                "turn-memory-pre-flight"
+            ],
+            "kinds": [
+                "target-write",
+                "prose"
+            ]
+        },
+        {
+            "token": "learn/agentos/decisions/0001-cross-process-cache-coherence.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/decisions/0001-cross-process-cache-coherence.md",
+            "referencingSkills": [
+                "structural-pre-flight"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/decisions/0002-phase3-wake-substrate-standards-alignment.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/decisions/0002-phase3-wake-substrate-standards-alignment.md",
+            "referencingSkills": [
+                "structural-pre-flight"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/decisions/0008-skill-anatomy-and-authoring-contract.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/agentos/decisions/0008-skill-anatomy-and-authoring-contract.md",
+            "referencingSkills": [
+                "create-skill"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/decisions/0018-neo-identity-source-of-truth-model.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/agentos/decisions/0018-neo-identity-source-of-truth-model.md",
+            "referencingSkills": [
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/DreamPipeline.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/DreamPipeline.md",
+            "referencingSkills": [
+                "industry-friction-radar",
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "load",
+                "target-write"
+            ]
+        },
+        {
+            "token": "learn/agentos/measurements/cognitive-load-baseline-2026-05.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/measurements/cognitive-load-baseline-2026-05.md",
+            "referencingSkills": [
+                "create-skill"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/measurements/pr-review-baseline-2026-04.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/measurements/pr-review-baseline-2026-04.md",
+            "referencingSkills": [
+                "pr-review"
+            ],
+            "kinds": [
+                "target-write"
+            ]
+        },
+        {
+            "token": "learn/agentos/ModelStats.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/ModelStats.md",
+            "referencingSkills": [
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "load",
+                "target-write"
+            ]
+        },
+        {
+            "token": "learn/agentos/NeuralLink.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/agentos/NeuralLink.md",
+            "referencingSkills": [
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "target-write"
+            ]
+        },
+        {
+            "token": "learn/agentos/process/contract-ledger.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/contract-ledger.md",
+            "referencingSkills": [
+                "create-skill",
+                "pr-review",
+                "ticket-create",
+                "ticket-intake"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/process/correction-culture.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/correction-culture.md",
+            "referencingSkills": [
+                "pr-review"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/process/evidence-ladder.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md",
+            "referencingSkills": [
+                "epic-resolution",
+                "epic-review",
+                "pr-review",
+                "pull-request"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/process/reference-hygiene.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/reference-hygiene.md",
+            "referencingSkills": [
+                "ideation-sandbox",
+                "pr-review",
+                "pull-request",
+                "ticket-create"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/process/SeatEvidenceCapabilities.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/agentos/process/SeatEvidenceCapabilities.md",
+            "referencingSkills": [
+                "pr-review",
+                "whitebox-e2e"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/tooling/Tier2RevalidationSweep.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/tooling/Tier2RevalidationSweep.md",
+            "referencingSkills": [
+                "ideation-sandbox"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/agentos/v13-path.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/v13-path.md",
+            "referencingSkills": [
+                "epic-review",
+                "session-sunset",
+                "structural-pre-flight"
+            ],
+            "kinds": [
+                "load",
+                "prose"
+            ]
+        },
+        {
+            "token": "learn/agentos/wake-substrate/NightShiftLeasedDriver.md",
+            "canonicalOwner": "neomjs/neo-agent-brain",
+            "resolution": "https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/wake-substrate/NightShiftLeasedDriver.md",
+            "referencingSkills": [
+                "post-review-pickup"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/benefits/ArchitectureOverview.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/benefits/ArchitectureOverview.md",
+            "referencingSkills": [
+                "industry-friction-radar",
+                "neo-identity-update",
+                "structural-pre-flight",
+                "tech-debt-radar",
+                "unit-test"
+            ],
+            "kinds": [
+                "load",
+                "target-write",
+                "prose"
+            ]
+        },
+        {
+            "token": "learn/benefits/body/Speed.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/benefits/body/Speed.md",
+            "referencingSkills": [
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/guides/fundamentals/CodebaseOverview.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/guides/fundamentals/CodebaseOverview.md",
+            "referencingSkills": [
+                "neo-identity-update"
+            ],
+            "kinds": [
+                "load",
+                "target-write"
+            ]
+        },
+        {
+            "token": "learn/guides/testing/UnitTesting.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/guides/testing/UnitTesting.md",
+            "referencingSkills": [
+                "unit-test"
+            ],
+            "kinds": [
+                "load"
+            ]
+        },
+        {
+            "token": "learn/guides/testing/WhiteboxE2E.md",
+            "canonicalOwner": "neomjs/neo",
+            "resolution": "https://github.com/neomjs/neo/blob/dev/learn/guides/testing/WhiteboxE2E.md",
+            "referencingSkills": [
+                "whitebox-e2e"
+            ],
+            "kinds": [
+                "load"
+            ]
+        }
+    ]
+}

package/.agents/skills/epic-resolution/references/epic-resolution-workflow.md

@@ -41,7 +41,7 @@ The shared matrix shape (used by both `epic-review` entry-pass and `epic-resolut
 For each parent AC of the epic:
 
 1. **Parent AC** — quote or reference the AC text from the epic body.
-2. **Required evidence** — L1 / L2 / L3 / L4 per the [Substrate Evidence Ladder](../../../../learn/agentos/process/evidence-ladder.md). The `epic-review` entry pass should have set this; if missing, derive from the AC text (does it require runtime / live / observable behavior?).
+2. **Required evidence** — L1 / L2 / L3 / L4 per the Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md). The `epic-review` entry pass should have set this; if missing, derive from the AC text (does it require runtime / live / observable behavior?).
 3. **Owning sub(s)** — the sub-issue(s) addressing this AC. From the epic's native sub-issue links (`update_issue_relationship` graph) or AC-explicit references.
 4. **Delivered PR(s)** — the merged PR(s) closing each sub. Use `gh pr list --search "linked-to:<sub-number>"` or check sub-issue's `closedByPullRequestsReferences`.
 5. **Achieved evidence** — read the merged PR body's `Evidence:` declaration. If two ceilings (sandbox vs achievable), report both: `L2 (sandbox) / L4 (achievable)`. If no Evidence declaration, mark as `L?? — declaration missing` and flag in residuals.
@@ -164,7 +164,7 @@ Per `feedback_a2a_commentid_pre_flight`: post the verdict comment FIRST, capture
 
 ## 7. Cross-references
 
-- `learn/agentos/process/evidence-ladder.md` — L1-L4 definitions + matrix schema authority
+- Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md) — L1-L4 definitions + matrix schema authority
 - `.agents/skills/epic-review/` — entry-pass sibling (seeds matrix at sub-creation time + Source Discussion Criteria Mapping per Stage 2.5 #11349)
 - `.agents/skills/pr-review/` — sub-execution gate (audits Evidence declaration on each merging PR)
 - `.agents/skills/pull-request/` — author-side Evidence declaration template

package/.agents/skills/epic-review/references/epic-review-workflow.md

@@ -93,11 +93,11 @@ Checks:
 - **Phase boundaries**: sub N's outputs feed sub N+1's inputs cleanly; no circular `blocked_by` dependencies
 - **Missing phases**: a prerequisite sub implied by the arc but not filed (e.g. a migration ticket, a schema ticket, a doc-update ticket)
 - **Scope creep risk**: subs whose titles or bodies exceed the parent epic's scope
-- **Structural Pre-Flight Sweep**: when subs prescribe new `.mjs` files (new daemon, new service, new script, new helper), validate each prescribed directory against `.agents/skills/structural-pre-flight/SKILL.md` Stage 0/1 BEFORE the sub is picked up. Each sub's PR will eventually have to satisfy this gate; surfacing mismatches at epic-review time is cheaper than at sub-PR-review time. Empirical anchor: M3 epic where sub PR #11008 misplaced `orchestrator-daemon.mjs` in `ai/scripts/` instead of v13-path.md M3 split (`ai/scripts/orchestrator-daemon.mjs` thin wrapper + `ai/daemons/Orchestrator.mjs` Neo-class + `ai/daemons/services/`); a Stage-3 sweep at epic-review would have caught the directory-choice mismatch in the prescription before sub pickup.
+- **Structural Pre-Flight Sweep**: when subs prescribe new `.mjs` files (new daemon, new service, new script, new helper), validate each prescribed directory against `.agents/skills/structural-pre-flight/SKILL.md` Stage 0/1 BEFORE the sub is picked up. Each sub's PR will eventually have to satisfy this gate; surfacing mismatches at epic-review time is cheaper than at sub-PR-review time. Empirical anchor: M3 epic where sub PR #11008 misplaced `orchestrator-daemon.mjs` in `ai/scripts/` instead of the Brain-owned [v13 path M3 split](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/v13-path.md) (`ai/scripts/orchestrator-daemon.mjs` thin wrapper + `ai/daemons/Orchestrator.mjs` Neo-class + `ai/daemons/services/`); a Stage-3 sweep at epic-review would have caught the directory-choice mismatch in the prescription before sub pickup.
 
 #### Stage 3.1 — Evidence Matrix Producer Hook (entry side of the closeout contract)
 
-*(Required when any of the epic's acceptance criteria describe observable runtime effect on a surface the CI / agent sandbox cannot reach — i.e., when the [Substrate Evidence Ladder](../../../../learn/agentos/process/evidence-ladder.md) trigger applies. Mark N/A for epics where ACs are fully covered by unit tests / static contract.)*
+*(Required when any of the epic's acceptance criteria describe observable runtime effect on a surface the CI / agent sandbox cannot reach — i.e., when the Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md) trigger applies. Mark N/A for epics where ACs are fully covered by unit tests / static contract.)*
 
 The `epic-review` skill is the *entry pass* of the closeout contract; `epic-resolution` is the *exit pass* (sibling skill, runs at sub-closure time). Both consume the same matrix shape on the parent epic body. **Stage 3.1 is where the entry pass SEEDS the matrix** so the exit pass has a contract to reconcile against.
 
@@ -114,7 +114,7 @@ For each parent AC of the epic, Stage 3 must produce columns 1–3 of the shared
 
 **Where the matrix lives:** post the Stage 3.1 matrix as a comment on the epic ticket, OR amend the epic body to include a `## Closeout Matrix (entry-seeded)` section. The closeout pass (`epic-resolution`) reads the most recent matrix-shaped artifact and reconciles columns 4–6 against the actual delivered PRs.
 
-**Cross-reference:** [`learn/agentos/process/evidence-ladder.md`](../../../../learn/agentos/process/evidence-ladder.md) for L1-L4 ladder + sandbox-vs-achievable ceiling distinction + complete schema definitions.
+**Cross-reference:** the Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md) for L1-L4 ladder + sandbox-vs-achievable ceiling distinction + complete schema definitions.
 
 ### Stage 4 — Prescription Layer
 
@@ -192,7 +192,7 @@ These citations belong in the `ticket-intake` reflection step for the sub, not a
 | `ticket-intake` | Sub pickup | Sub-scope | Epic-review runs *before* ticket-intake the first time your identity picks up any sub from this epic. After epic-review, ticket-intake proceeds per its own protocol. |
 | `pull-request` | PR creation | PR-scope | Orthogonal — epic-review does not interact with the PR layer. |
 | `pr-review` | PR validation | Post-work | Complementary — epic-review catches scope/approach drift *before* work; pr-review catches execution drift *after*. Different blast radius, different timing. |
-| `epic-resolution` | Epic closeout | At sub-closure time | Sibling exit-pass to this entry-pass. Epic-review Stage 3.1 SEEDS the AC → required-evidence → owning-sub matrix; epic-resolution RECONCILES columns 4–6 (delivered PRs / achieved evidence / residual state) at closeout time. The two skills share the same matrix schema defined in [`learn/agentos/process/evidence-ladder.md`](../../../../learn/agentos/process/evidence-ladder.md). Different agents may run the two passes; the matrix-as-artifact is the contract between them. |
+| `epic-resolution` | Epic closeout | At sub-closure time | Sibling exit-pass to this entry-pass. Epic-review Stage 3.1 SEEDS the AC → required-evidence → owning-sub matrix; epic-resolution RECONCILES columns 4–6 (delivered PRs / achieved evidence / residual state) at closeout time. The two skills share the same matrix schema defined in the Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md). Different agents may run the two passes; the matrix-as-artifact is the contract between them. |
 
 ## 7. Anti-Patterns
 

package/.agents/skills/ideation-sandbox/audits/tier-2-revalidation.md

@@ -68,7 +68,7 @@ The mechanism is intentionally narrow:
 | Discussion [#11793 OQ5](https://github.com/neomjs/neo/discussions/11793) | Deferred-with-timeline that produced this mechanism |
 | `ai/graph/identityRoots.mjs` | `participationStatus` + `since` + `reactivationTrigger` source-of-truth |
 | `ai/scripts/revalidationSweep.mjs` | Implementation |
-| `learn/agentos/tooling/Tier2RevalidationSweep.md` | Operator runbook (when-to-invoke, mechanism, invocation, MVP scope boundaries) |
+| Brain-owned [Tier-2 Revalidation Sweep operator runbook](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/tooling/Tier2RevalidationSweep.md) | When-to-invoke, mechanism, invocation, and MVP scope boundaries |
 | `.agents/skills/ideation-sandbox/audits/consensus-mandate.md` §quorum-rule | Tier-2 rule background |
 
 ## §empirical-anchor — Dogfooded Match

package/.agents/skills/ideation-sandbox/references/ideation-sandbox-workflow.md

@@ -29,7 +29,7 @@ Before drafting a Discussion/proposal, run [`../audits/pre-authoring-adjacency-s
 
 ### 2.1 Reference Hygiene
 
-Before Discussion prose, read [`reference-hygiene.md`](../../../../learn/agentos/process/reference-hygiene.md): relationships stay bare; descriptive tokens use backticks.
+Before Discussion prose, read the Brain-owned [reference-hygiene contract](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/reference-hygiene.md): relationships stay bare; descriptive tokens use backticks.
 
 ### 2.2 Provenance Signature
 

package/.agents/skills/industry-friction-radar/references/industry-friction-radar-workflow.md

@@ -57,8 +57,8 @@ You must use the `ideation-sandbox` skill to post a GitHub Discussion proposing
 
 To understand the macro-architecture this skill serves (Neo as an Application Engine on the Left Hemisphere, and Agent OS on the Right Hemisphere), review the following:
 
-- `learn/benefits/ArchitectureOverview.md` (Left/Right Hemispheres)
-- `learn/agentos/DreamPipeline.md` (Sensory Input & DreamService)
+- Engine-owned [Architecture Overview](https://github.com/neomjs/neo/blob/dev/learn/benefits/ArchitectureOverview.md) (Left/Right Hemispheres)
+- Brain-owned [Dream Pipeline](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/DreamPipeline.md) (Sensory Input & DreamService)
 - `resources/content/discussions/discussion-10119.md` (Engine-category vs. Framework-category positioning)
 - `resources/content/discussions/discussion-10137.md` (Agent OS context)
 - `.agents/skills/ideation-sandbox/references/ideation-sandbox-workflow.md` (Pre-Filing Precedent Sweep): The radar targets *frontier friction* where standards are failing. The `ideation-sandbox` precedent sweep targets *established standards* to avoid reinventing them. They are complementary disciplines.

package/.agents/skills/neo-identity-update/SKILL.md

@@ -7,4 +7,4 @@ description: "Repeatable protocol for updating Neo's identity (what Neo IS) cohe
 
 Neo's identity is distributed across ~30+ surfaces; editing one (e.g. README) leaves machine-facing JSON, build-generated SEO files, external platform settings, and CTA targets drifting silently. Before changing ANY identity surface (tagline, description, keywords, pillar story, CTA / next-step door, or a drifted fact like version / MCP-server-count / Node-req), you MUST read `.agents/skills/neo-identity-update/references/update-protocol.md` and follow it — it routes to the surface inventory, facts ledger, framing-governance payload, and CTA-governance payload.
 
-**Non-negotiables:** FACTS converge to one source (derive/coherence-check the rest); FRAMING stays audience-segmented against the README apex (escalate contradictions, never find-replace); ACTIONS / CTAs keep pitches from dead-ending and surface proof without inventing business-owned offer content; never edit build-generated output (edit the generator `buildScripts/docs/seo/generate.mjs`); every identity-surface PR needs a cross-family review; never name a client/partner/customer. Foundation: [ADR 0018](../../../learn/agentos/decisions/0018-neo-identity-source-of-truth-model.md).
+**Non-negotiables:** FACTS converge to one source (derive/coherence-check the rest); FRAMING stays audience-segmented against the README apex (escalate contradictions, never find-replace); ACTIONS / CTAs keep pitches from dead-ending and surface proof without inventing business-owned offer content; never edit build-generated output (edit the generator `buildScripts/docs/seo/generate.mjs`); every identity-surface PR needs a cross-family review; never name a client/partner/customer. Foundation: [ADR 0018](https://github.com/neomjs/neo/blob/dev/learn/agentos/decisions/0018-neo-identity-source-of-truth-model.md).

package/.agents/skills/neo-identity-update/references/affected-areas-map.md

@@ -13,9 +13,9 @@ Markdown a human edits directly. Failure mode: generations drift apart (one doc
 | `CONTRIBUTING.md`, `.github/GETTING_STARTED.md`, `.github/AI_QUICK_START.md` | Contributor-facing identity; MCP-server count; Node requirement |
 | `.github/STORY.md` | **Public-era heritage SSOT**: origin narrative, 2015 worker POC, public GitHub start, JSON-first VDOM, worker-first architecture, multi-window line. |
 | `.github/NEOMJS_HISTORY.md` | Pre-public contributor credits / acknowledgements archive. Do **not** extend it with public-era milestones unless an explicit operator ruling changes its document kind. |
-| `learn/benefits/**` | Engineering-altitude identity (ArchitectureOverview "Two Hemispheres", Introduction, comparisons/NeoVs*); the **RIGHT-hemisphere AI-team doc lives here** |
-| `learn/agentos/*.md` | Mechanism-altitude (DreamPipeline, MX, MemoryCore, NeuralLink); the recurring motto |
-| `.claude/CLAUDE.md` (§neo_identity_anchor, §swarm_topology_anchor), `learn/agentos/AGENTS_ATLAS.md` | Agent-facing identity anchors; maintainer roster; pillar definitions |
+| Engine-owned benefits corpus ([Architecture Overview](https://github.com/neomjs/neo/blob/dev/learn/benefits/ArchitectureOverview.md) entry point) | Engineering-altitude identity (Two Hemispheres, Introduction, comparisons/NeoVs*); the **RIGHT-hemisphere AI-team doc lives here** |
+| Canonical mechanism guides in their owning repositories — Brain-owned [Dream Pipeline](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/DreamPipeline.md) and Engine-owned [Neural Link](https://github.com/neomjs/neo/blob/dev/learn/agentos/NeuralLink.md) entry points | Mechanism-altitude identity (Dream Pipeline, MX, Memory Core, Neural Link); the recurring motto |
+| `.claude/CLAUDE.md` (§neo_identity_anchor, §swarm_topology_anchor), Engine-owned [Agent OS Atlas](https://github.com/neomjs/neo/blob/dev/learn/agentos/AGENTS_ATLAS.md) | Agent-facing identity anchors; maintainer roster; pillar definitions |
 
 ## Class 2 — generated-output-source (THE TRAP)
 A build script emits the surface. **Edit the generator, never the output.**
@@ -47,13 +47,13 @@ Correct as-of a date; ages silently. Refresh in lock-step.
 
 | Surface | Lock-step sibling |
 |---|---|
-| `README.md` "A Platform at Scale (State of <date>)" | `learn/guides/fundamentals/CodebaseOverview.md` (canonical numbers) |
-| `ROADMAP.md` velocity metrics; `learn/agentos/ModelStats.md` | their own as-of dates |
+| `README.md` "A Platform at Scale (State of <date>)" | Engine-owned [Codebase Overview](https://github.com/neomjs/neo/blob/dev/learn/guides/fundamentals/CodebaseOverview.md) (canonical numbers) |
+| `ROADMAP.md` velocity metrics; Brain-owned [Model Stats](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/ModelStats.md) | their own as-of dates |
 
 ## Coverage notes
 - Heritage facts live in `.github/STORY.md`; README + portal About Us reference that home without duplicating milestone lists. OS-Awards claims need an acceptable external public source before publication.
-- Identity handles are routed through `ai/graph/identityRoots.mjs`; handle de-versioning is operator-owned (account rename), the skill only propagates. Model-version stays in `ModelStats.md` per ADR 0012. Re-run a seam-keyed grep before claiming total coverage.
-- Not yet fully swept: `apps/portal/view/about` (`/about-us`), live neomjs.com `<meta>`/ld+json, `learn/comparisons/*`. Re-run a fan-out before claiming total coverage.
+- Identity handles are routed through `ai/graph/identityRoots.mjs`; handle de-versioning is operator-owned (account rename), the skill only propagates. Model-version stays in the Brain-owned [Model Stats guide](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/ModelStats.md) per ADR 0012. Re-run a seam-keyed grep before claiming total coverage.
+- Not yet fully swept: `apps/portal/view/about` (`/about-us`), live neomjs.com `<meta>`/ld+json, and the Engine-owned comparisons corpus. Re-run a fan-out before claiming total coverage.
 
 ## ACTIONS / CTA overlay
 
@@ -67,7 +67,7 @@ the business-owned content behind them.
 | `README.md` opening + v13 Agent OS pitch | Proof doors for public repo claims; product / deployment next-step door if the pitch asks the reader to act |
 | `README.md` Quickstart | Install door (`npx neo-app@latest`) plus getting-started docs |
 | `README.md` Community / Contributing | Community and contributor doors; channel liveness and retention must be checked before primary placement |
-| `learn/benefits/**`, `learn/agentos/**` | Learn / proof / contribute doors attached to identity claims and Agent OS mechanisms |
+| Engine-owned benefits guides plus Agent OS guides in their canonical Engine or Brain repository | Learn / proof / contribute doors attached to identity claims and Agent OS mechanisms |
 | `apps/portal/view/home/parts/*.mjs` | Portal hero / home-page CTA doors; generated SEO siblings may also need generator updates |
 | `apps/portal/view/services/**`, `apps/portal/resources/data/seo.json` | Services / contact / training doors; content is business-owned and must not be invented by the skill |
 | `buildScripts/docs/seo/generate.mjs` | Generated `llms.txt` / sitemap route doors; edit the generator, never generated output directly |

package/.agents/skills/neo-identity-update/references/facts-ledger.md

@@ -4,12 +4,12 @@ Each identity FACT has ONE canonical source. Every other occurrence derives from
 
 | Fact | Canonical SSOT | Propagate by | Known stale-prone occurrences |
 |---|---|---|---|
-| **Package version** | `package.json` `version` | extend `buildScripts/release/prepare.mjs` to derive version-bearing structured surfaces + `learn/agentos/NeuralLink.md` version line; coherence-check the rest | `NeuralLink.md`; `FooterContainer.mjs` literal |
+| **Package version** | `package.json` `version` | extend `buildScripts/release/prepare.mjs` to derive version-bearing structured surfaces + the Engine-owned [Neural Link guide](https://github.com/neomjs/neo/blob/dev/learn/agentos/NeuralLink.md) version line; coherence-check the rest | Engine-owned Neural Link guide; `FooterContainer.mjs` literal |
 | **MCP-server count / audience split** | `package.json` scripts matching `ai:mcp-server-*` — NOT `ls ai/mcp/server/` (that returns 7: it includes `shared/` infra + `gitlab-workflow/` PoC; functional = 5: knowledge-base, memory-core, github-workflow, neural-link, file-system). Frontier-harness defaults expose 4 because Codex, Claude, Gemini CLI, and Antigravity already provide native filesystem/tools; file-system is for `Neo.ai.Agent` / local harnessless loops. | derive into prose/JSON or lint coherence-check against the script manifest plus the audience split | README; AI_QUICK_START; ApplicationEngine.md; index.html FAQ; AiToolchain.mjs; llms.txt header |
 | **Node requirement** | `package.json` `engines.node` | derive doc mentions; lint | AI_QUICK_START; structured-data `softwareRequirements` if reintroduced |
-| **Identity handle** | `ai/graph/identityRoots.mjs` | route references through the seam. Account rename is operator-owned (Tier-4); the skill propagates. Model-version stays in `ModelStats.md` per ADR 0012 — do NOT de-version the prose | hand-maintained current surfaces can retain stale handles after a graph/code migration; re-run a seam-keyed grep |
-| **Recurring motto** | `learn/agentos/DreamPipeline.md` (origin of "the system evolves by predicting its own evolution") | reference a single quotable constant; don't re-type | DreamPipeline (2×), README, ROADMAP |
-| **Codebase-scale metrics** | `learn/guides/fundamentals/CodebaseOverview.md` | README "Platform at Scale" refreshes in lock-step; carry an explicit as-of date | README |
+| **Identity handle** | `ai/graph/identityRoots.mjs` | route references through the seam. Account rename is operator-owned (Tier-4); the skill propagates. Model-version stays in the Brain-owned [Model Stats guide](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/ModelStats.md) per ADR 0012 — do NOT de-version the prose | hand-maintained current surfaces can retain stale handles after a graph/code migration; re-run a seam-keyed grep |
+| **Recurring motto** | Brain-owned [Dream Pipeline guide](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/DreamPipeline.md) (origin of "the system evolves by predicting its own evolution") | reference a single quotable constant; don't re-type | Dream Pipeline (2×), README, ROADMAP |
+| **Codebase-scale metrics** | Engine-owned [Codebase Overview](https://github.com/neomjs/neo/blob/dev/learn/guides/fundamentals/CodebaseOverview.md) | README "Platform at Scale" refreshes in lock-step; carry an explicit as-of date | README |
 | **GA / public repo start date** | first git commit (`git log --reverse`, = `2019-11-11`) | heritage = append-only; write once into `.github/STORY.md` | README / portal should reference the story, not duplicate the date |
 
 ## Propagation mechanism — preference order
@@ -22,7 +22,7 @@ When the right mechanism doesn't exist yet (e.g. no lint guard for server count)
 
 ## Verified anchors (re-verify before citing publicly)
 - GA / first commit: **November 2019** (`git log --reverse` → `2019-11-11`). "JSON-first since 2019" is correct.
-- Performance: `learn/benefits/Speed.md` — consistent **20,000+** DOM-updates/sec floor, observed peak **over 40,000**. Cite as observed-peak (+ floor), not a guaranteed benchmark.
+- Performance: Engine-owned [Speed guide](https://github.com/neomjs/neo/blob/dev/learn/benefits/body/Speed.md) — consistent **20,000+** DOM-updates/sec floor, observed peak **over 40,000**. Cite as observed-peak (+ floor), not a guaranteed benchmark.
 - Velocity counts: publish as a **dated-window stat** with the inline range (e.g. "2026-04-30 → 2026-05-30"), regenerated from `git`/GitHub API — never an audited absolute.
 - Heritage home: `.github/STORY.md`. `.github/NEOMJS_HISTORY.md` is pre-public contributor credits / acknowledgements; do not expand it with public-era milestones.
 - OS-Awards 2021: **not repo-verifiable** — confirm exact name/category/placement from an external source before any public citation.

package/.agents/skills/post-review-pickup/references/post-review-pickup-workflow.md

@@ -36,8 +36,8 @@ file or route the bug, then continue picking the next lane.
   role payloads must be read before lane choice, and when review-first is
   legitimate.
 
-<!-- trigger: watchdog/night-shift wake, operator driver command, or lane-driver handoff → read learn/agentos/wake-substrate/NightShiftLeasedDriver.md -->
-- `learn/agentos/wake-substrate/NightShiftLeasedDriver.md` — TTL, renewal, and
+<!-- trigger: watchdog/night-shift wake, operator driver command, or lane-driver handoff → read https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/wake-substrate/NightShiftLeasedDriver.md -->
+- Brain-owned [night-shift leased-driver runbook](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/wake-substrate/NightShiftLeasedDriver.md) — TTL, renewal, and
   direct-driver routing for autonomous windows. A lane-ownership contract, not a
   review-pickup variant.
 

package/.agents/skills/pr-review/assets/pr-review-template.md

@@ -124,7 +124,7 @@ For every issue named as close-target, verify it does NOT carry the `epic` label
 
 *(Required when the PR's close-target ACs include observable runtime effect on a surface the CI / agent sandbox cannot reach — substrate / harness / wake / restart / UI-with-visual-AC / CLI-with-host-behavior PRs. This is part of the 10% AC/audit sanity layer: binding on real evidence mismatch, not a replacement for architecture review. Mark N/A for PRs where ACs are fully covered by unit tests / static contract.)*
 
-Reference: [`learn/agentos/process/evidence-ladder.md`](../../../../learn/agentos/process/evidence-ladder.md) for L1-L4 ladder + sandbox-vs-achievable ceiling distinction.
+Reference: the Brain-owned [Substrate Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md) for L1-L4 ladder + sandbox-vs-achievable ceiling distinction.
 
 The PR body must declare achieved evidence in 1-line greppable form:
 

package/.agents/skills/pr-review/references/measurement-methodology.md

@@ -26,10 +26,10 @@ For subsequent re-reviews (Cycle N), the measurement must capture the delta payl
 
 ## 3. Baseline Data Capture
 Before any pilot extraction (Sub-issue 2 of Epic #10537) can begin, we must capture a **minimum of 10 cycles** of baseline data. If statistical variance remains high at n=10, capture will extend to n=15 or n=20 before proceeding, to avoid extracting based on noisy or atypical cycle data.
-- The recorded data must be appended to the dedicated tracking file: `learn/agentos/measurements/pr-review-baseline-2026-04.md`.
+- The recorded data must be appended to the dedicated [PR-review baseline measurement log](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/measurements/pr-review-baseline-2026-04.md) in the Brain repository. If the current checkout is not Brain, route the write to a Brain change instead of creating a consumer-local copy.
 - **Gating Mechanism:** Sub-issue 2 (Pilot extraction of review templates) is strictly blocked until the baseline (per §3 opening) is fully captured and validated.
 
 ## 4. Execution Procedure
 1. During a PR Review, calculate the `wc -c` of the relevant files and payloads (separating Static vs Dynamic).
 2. Log the cycle details, including PR number, Cycle number, Static `wc -c`, Dynamic `wc -c`, and Total `wc -c`.
-3. Report the log natively in your PR Review comment as a `Measurement Payload` block. A dedicated aggregator or the author during session sunset will persist it to `learn/agentos/measurements/pr-review-baseline-2026-04.md` to avoid review-time merge conflicts.
+3. Report the log natively in your PR Review comment as a `Measurement Payload` block. A dedicated aggregator or the author during session sunset will persist it to the Brain repository's [PR-review baseline measurement log](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/measurements/pr-review-baseline-2026-04.md) to avoid review-time merge conflicts; a non-Brain checkout must route that write to Brain.

package/.agents/skills/pr-review/references/pr-review-guide.md

@@ -14,7 +14,7 @@ This protocol ensures that feedback is:
 
 Build — and write down — your premise of the change **before** reading the patch as the source of truth. You can reject a toaster-when-we-need-a-car before reading a line; a green checklist over a wrong premise is theater. Capture four fields. The snapshot is **patch-blind** — the *premise authority* is the substrate, not the patch ("I wrote this first" is itself theater).
 
-1. **Inputs read before the patch** — the ticket/issue, the changed-file list, the current `dev` source of the touched files, sibling precedent, and the source-of-authority substrate (ADRs, `learn/`, the owning service). **NOT the PR's own self-description as the primary premise** — the PR body is a claim to verify, not the authority. Build the premise from the affected files (intent belongs in their JSDoc — `src/core/Base.mjs` is the bar), their neighbors, and their imports; use `memory-mining` / `ask_knowledge_base` when the code is thin. Intent you can't find anywhere is the finding: ticket the gap. **Intent authority:** PR claims to change / retire / amend / supersede / correct a prior position → mine the body's `Origin Session ID`: the premise is intent-vs-diff, not claims-vs-diff, and semantic search misses silently ([correction-culture](../../../../learn/agentos/process/correction-culture.md)).
+1. **Inputs read before the patch** — the ticket/issue, the changed-file list, the current `dev` source of the touched files, sibling precedent, and the source-of-authority substrate (ADRs, `learn/`, the owning service). **NOT the PR's own self-description as the primary premise** — the PR body is a claim to verify, not the authority. Build the premise from the affected files (intent belongs in their JSDoc — `src/core/Base.mjs` is the bar), their neighbors, and their imports; use `memory-mining` / `ask_knowledge_base` when the code is thin. Intent you can't find anywhere is the finding: ticket the gap. **Intent authority:** PR claims to change / retire / amend / supersede / correct a prior position → mine the body's `Origin Session ID`: the premise is intent-vs-diff, not claims-vs-diff, and semantic search misses silently (see the [correction-culture guide](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/correction-culture.md)).
 2. **Expected solution-shape** (1–3 sentences) — what *should* a correct change here look like? Explicitly include **"what boundary should this NOT hardcode?"** and **"what test-isolation should exist?"**, so the snapshot reaches the portability + test-isolation dimensions before the diff frames them away.
 3. **Patch-verdict** — does the diff **match / improve / contradict** the expected shape? Name the specific evidence that changed (or confirmed) your mind. "Matches" with no evidence is not a verdict.
 4. **Premise-coherence** — the value-coherence verdict, or a scoped "N/A — no value-surface".
@@ -84,7 +84,7 @@ The Retrospective daemon explicitly regex-matches these tags during REM sleep:
 
 ### 4.1 Reference Hygiene
 
-Before review prose/tags, read [`reference-hygiene.md`](../../../../learn/agentos/process/reference-hygiene.md): structural tokens stay bare; descriptive tokens use backticks.
+Before review prose/tags, read the [reference-hygiene guide](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/reference-hygiene.md): structural tokens stay bare; descriptive tokens use backticks.
 
 ## 5. Required Actions & Cross-Linking
 *   **Related Graph Nodes:** Every PR review MUST list related graph nodes (e.g., `Target Epic ID`, `Issue ID`) to ensure the Native Edge Graph links the evaluation to the overarching goal.
@@ -129,7 +129,7 @@ For PRs that introduce or modify public/consumed surfaces (e.g., configs, MCP to
 1. **Locate the Ledger:** Fetch the originating ticket (the close-target). Look for the "Contract Ledger" markdown table in the ticket body. If it is a sub-issue relying on a parent epic's ledger, fetch the parent epic to locate it.
 2. **Missing Ledger:** If the PR modifies public surfaces but both the originating ticket and its parent epic lack a Contract Ledger, flag as a **Required Action**:
    > *"PR modifies public/consumed surfaces but the originating ticket (and parent epic) lacks a Contract Ledger matrix. Required: backfill the Contract Ledger on the ticket to establish the formal API contract."*
-3. **Drift Detection:** Compare the PR diff against the ticket's Contract Ledger. If the implemented contract drifts from the ledger (e.g., added fields, changed types, missing deprecation steps), or if a ledger row fails the Surface-Anchor V-B-A in `learn/agentos/process/contract-ledger.md`, flag as a **Required Action**:
+3. **Drift Detection:** Compare the PR diff against the ticket's Contract Ledger. If the implemented contract drifts from the ledger (e.g., added fields, changed types, missing deprecation steps), or if a ledger row fails the Surface-Anchor V-B-A in the [Contract Ledger protocol](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/contract-ledger.md), flag as a **Required Action**:
    > *"Contract drift detected: the implementation differs from the Contract Ledger defined in the ticket. Required: update the ticket's Contract Ledger to reflect the exact shipped reality."*
 
 The PR cannot be approved if the implemented contract and the ticket's Contract Ledger are out of sync.
@@ -256,7 +256,7 @@ Demo/product-surface diffs touching rendered motion: load `audits/demo-surface-m
 
 ### 7.5.4 Seat Routing
 
-Before claiming/requesting visual-render, headed-harness, or native-matrix evidence: consult `learn/agentos/process/SeatEvidenceCapabilities.md` (check `observedAt`; stale = `unknown`).
+Before claiming/requesting visual-render, headed-harness, or native-matrix evidence: consult the Engine's [Seat Evidence Capabilities guide](https://github.com/neomjs/neo/blob/dev/learn/agentos/process/SeatEvidenceCapabilities.md) (check `observedAt`; stale = `unknown`).
 
 ### 7.6 CI / Security Checks Audit
 

package/.agents/skills/pull-request/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pull-request
-description: "Standardized guidelines and procedural execution flow for opening a Pull Request. CRITICAL: Do NOT run default `npx playwright test` (use custom configs). MANDATORY ROI WARNING: Skipping the PR body template guarantees CI lint failure. Triggers: Code modifications complete; before opening PR — stepping-back reflection, commit format, cross-family review mandate, post-comment A2A commentId hand-off (author→reviewer) per review-response-protocol.md §14, Evidence declaration line for substrate/runtime-AC PRs per [evidence-ladder.md](learn/agentos/process/evidence-ladder.md)."
+description: "Standardized guidelines and procedural execution flow for opening a Pull Request. CRITICAL: Do NOT run default `npx playwright test` (use custom configs). MANDATORY ROI WARNING: Skipping the PR body template guarantees CI lint failure. Triggers: Code modifications complete; before opening PR — stepping-back reflection, commit format, cross-family review mandate, post-comment A2A commentId hand-off (author→reviewer) per review-response-protocol.md §14, Evidence declaration line for substrate/runtime-AC PRs per the [Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md)."
 ---
 # Pull Request Skill