@event4u/agent-config 14.12.0 → 14.14.0

package/docs/guidelines/agent-infra/reuse-verdict-mechanics.md

@@ -0,0 +1,71 @@
+# Reuse-verdict mechanics — the verdict set, the cheap question, and the routing that was refused
+
+> The detail behind § 8b of
+> [`agent-interaction-and-decision-quality`](agent-interaction-and-decision-quality.md),
+> which [`improve-before-implement`](../../../src/rules/improve-before-implement.md)
+> routes to. It lives here rather than inline because that guideline sits at the
+> 16,000-char depth ceiling `check_depth_budget` holds as a growth ratchet, and
+> the gate states plainly that raising its baseline is a defect rather than a fix.
+
+## 8b-verdict. The verdict set, and what `new` owes
+
+The ladder's answer is a **named verdict, never a yes/no**:
+
+| verdict | meaning |
+|---|---|
+| `reuse` | the existing thing carries the requirement as-is |
+| `extract` | it carries it once a shared part is pulled out |
+| `refactor` | it carries it once reshaped, same responsibility |
+| `extend` | it carries it with an added, non-distorting case |
+| `migrate` | it should carry it, and the move is the work |
+| `new` | nothing carries it, and the search that establishes that is the evidence |
+
+**`new` owes negative evidence** — the closest existing candidate **by name and
+path**, and why it does not carry the requirement. *"Nothing similar exists"*
+naming no candidate is an unrun search, not an answer, and it is the shape this
+verdict set exists to make visible.
+
+Two clauses hold the set honest, and both cut against reading it as a ranking:
+
+- **The order is a thinking preference, not a ranking.** A `new` after a real
+  search beats an `extend` that bends a helper out of shape. Preferring reuse is
+  not preferring reuse *at any cost*.
+- **Textual similarity alone is never grounds for an abstraction.** Two blocks
+  that read alike and change for different reasons are two blocks — the
+  per-class bars are in [`abstraction-thresholds`](../abstraction-thresholds.md).
+
+**Reach the verdict with the engine, not a fresh grep protocol.** `agent-config
+code-graph query` and `code-graph affected`;
+[`external-code-graph-interop`](../../../src/rules/external-code-graph-interop.md)
+already mandates query-before-grep and names grep the fallback, so a second
+search specification here would contradict it rather than add to it.
+
+## 8b-cheap. Why the exclusions buy the checks and never the question
+
+The rule excludes bug fixes, config changes, user-fenced tasks and trivial
+changes from the **three heavy checks**. The one cheap question — *does this
+already exist in the tree* — fires on all four rows anyway.
+
+The reason is empirical rather than tidy: **bug fixes and renames re-add an
+existing helper more often than features do**, because the author is inside one
+file and reaching for something small. Switching the reuse rung off there
+switches it off where it pays most.
+
+Cheap means cheap, on the [`ui-audit-gate`](../../../src/rules/ui-audit-gate.md)
+precedent: one `code-graph query`, one named verdict, no interview.
+
+**The skip is decidable from the diff alone** — ≤ 1 file, ≤ 5 changed lines, no
+new symbol, no new dependency. A typo satisfies all four with no state to
+consult; an added symbol never does.
+
+## 8b-routing. Why this is not routed through the TDD cluster
+
+Two source proposals put the existence question in `/tdd`'s design mode, as the
+one point every behavior passes through. **It cannot live there, and the reason
+is delivery rather than design:**
+`src/domains/engineering-base/tdd/command.md` carries `visibility: internal` and
+`disable-model-invocation: true`, so **a consumer cannot reach it.** The routing
+is undeliverable, not merely unwanted.
+
+Recorded here so the next author does not re-derive the proposal and re-propose
+it.

package/docs/guidelines/agent-infra/review-routing-data-format.md

@@ -1,8 +1,8 @@
 # Review Routing Data Format
 
 Schema and conventions for the two project-local YAML files that feed the
-[`reviewer-awareness`](../../rules/reviewer-awareness.md) rule
-and the [`review-routing`](../../skills/review-routing/SKILL.md) skill.
+[`reviewer-awareness`](../../../src/rules/reviewer-awareness.md) rule
+and the [`review-routing`](../../../src/skills/review-routing/SKILL.md) skill.
 
 Both files are **optional** and live in the consumer repository — never
 in package-shipped artifacts. Absence is handled gracefully: routing
@@ -69,7 +69,7 @@ Field semantics:
   `pr-risk-config.yml`. First match wins; later entries are ignored for
   that path.
 - **roles** (required, list) — role identifiers from the common
-  vocabulary in [`reviewer-awareness`](../../rules/reviewer-awareness.md)
+  vocabulary in [`reviewer-awareness`](../../../src/rules/reviewer-awareness.md)
   or project-custom roles.
 - **focus** (optional, string) — one-line description of what reviewers
   should look at. Surfaced in the PR comment verbatim.
@@ -124,8 +124,8 @@ Field semantics:
   diff when **any** changed file matches any glob.
 - **required_test** (required, string) — the specific assertion or
   regression test the pattern demands. Feeds
-  [`verify-before-complete`](../../rules/verify-before-complete.md) and
-  [`judge-test-coverage`](../../skills/judge-test-coverage/SKILL.md).
+  [`verify-before-complete`](../../../src/rules/verify-before-complete.md) and
+  [`judge-test-coverage`](../../../src/skills/judge-test-coverage/SKILL.md).
 - **references** (optional, list) — links to prior PRs, incidents, or
   postmortems. Agents quote these verbatim when warning about a match.
 
@@ -139,5 +139,5 @@ Field semantics:
 
 ## See also
 
-- [`reviewer-awareness`](../../rules/reviewer-awareness.md)
-- [`review-routing`](../../skills/review-routing/SKILL.md)
+- [`reviewer-awareness`](../../../src/rules/reviewer-awareness.md)
+- [`review-routing`](../../../src/skills/review-routing/SKILL.md)

package/docs/guidelines/agent-infra/roadmap-progress-mechanics.md

@@ -10,7 +10,7 @@ _Origin: migrated from `.agent-src.uncondensed/rules/roadmap-progress-sync.md` p
 # Roadmap Progress Sync
 
 > **Enforced by (defence in depth):**
-> 1. [`scripts/roadmap_progress_hook.ts`](../../src/scripts/roadmap_progress_hook.ts)
+> 1. [`scripts/roadmap_progress_hook.ts`](../../../src/scripts/roadmap_progress_hook.ts)
 >    on Augment + Claude Code (`PostToolUse`) — auto-regen on write.
 > 2. `.git/hooks/pre-commit` (installed by `scripts/install-hooks.sh`) —
 >    blocks any commit whose staged set touches `agents/roadmaps/` or
@@ -147,7 +147,7 @@ dashboard, commit if commit policy allows.
 A reply that lands a verified step without flipping its checkbox is a rule violation.
 
 **Deterministic flip-guard.** The autonomous loop carries a per-step
-guard at [`roadmap-process-loop § 5b`](../../.agent-src.uncondensed/contexts/execution/roadmap-process-loop.md#5b-flip-guard--deterministic):
+guard at [`roadmap-process-loop § 5b`](../../../src/agent-src/contexts/execution/roadmap-process-loop.md#5b-flip-guard--deterministic):
 after the atomic flip, the loop runs
 `git diff --name-only -- agents/roadmaps/<file>.md` and halts loudly
 when the diff is empty. The `command:` triggers on
@@ -164,11 +164,13 @@ the step lands; that's a normal `[ ] → [x]` transition.
 ## Mechanics — triggers, regen command, self-check, failures
 
 The triggers table, the regen command (`./agent-config roadmap:progress`),
-the mandatory pre-send self-check, the failure-mode catalog, and the
-`Do NOT` list live in
-[`contexts/communication/rules-auto/roadmap-progress-sync-mechanics.md`](../contexts/communication/rules-auto/roadmap-progress-sync-mechanics.md).
-Pull it whenever a trigger fires — the rule above is the obligation
-surface; the mechanics file is the lookup material.
+the pre-send self-check, the failure-mode catalog and the `Do NOT` list are
+**in this file**; the rule
+[`roadmap-progress-sync`](../../../src/rules/roadmap-progress-sync.md) is the
+obligation surface.
+
+> **Corrected 2026-08-26.** This pointed at a `rules-auto` mechanics file that
+> exists nowhere — a split that never happened, while the content was here.
 
 ## Copilot fallback
 
@@ -218,6 +220,10 @@ Keep aligned with the dashboard counter in `scripts/update_roadmap_progress.ts`
 
 `[~]` is **not** an "in-progress" indicator. Mid-reply work-in-flight has no checkbox change until the step lands; that's a normal `[ ] → [x]` transition.
 
+#### `guarded-baseline` — a sub-state of `[ ]`, never a fifth glyph
+
+See [`guarded-baseline`](guarded-baseline.md).
+
 **Dashboard regen cadence — opt-in batching.** The checkbox flip is non-batchable. The **subprocess regen** (`./agent-config roadmap:progress`) is batchable per `roadmap.dashboard_regen_cadence` in `.agent-settings.yml` (`every_5_steps` default · `per_step` · `phase_boundary`). Run end, phase boundary, and any file-shape touch (rename / phase add / archive — Iron Law 1) always force an immediate regen regardless of cadence.
 
 **Blockers follow the same cadence as checkboxes.** Clearing a `## Blockers` entry (per `templates/roadmaps.md` rule 20) flips its `Status: resolved` and regenerates the dashboard in the same reply — Iron Law 1's "same response" obligation applies to blocker resolution exactly as it applies to a checkbox flip.

package/docs/guidelines/agent-infra/role-contracts.md

@@ -77,7 +77,7 @@ Referenced by `road-to-role-modes.md` Phase 1. Each contract is a
 mode exits, the agent MUST either emit an intake signal via
 [`memory-access`](memory-access.md) (`scripts/memory_signal.ts`
 append — one line, fire-and-forget) or draft a curated entry with
-[`/memory-add incident-learnings`](../../commands/memory-add.md).
+[`/memory-add incident-learnings`](../../../src/domains/meta/memory/add/command.md).
 Pattern + consequence + guardrail, redacted. Skipping this field
 means the incident did not produce a learning — log the absence,
 do not pretend verification happened.
@@ -150,7 +150,7 @@ output contract.
 
 This table is **advisory**, not enforcing. A skill may cite any
 persona inside any mode; the mapping below is just the most common
-fit. See [`../../personas/README.md`](../../personas/README.md) for
+fit. See [`../../personas/README.md`](../../../src/agent-src/personas/README.md) for
 the persona catalog and schema.
 
 | Mode | Typical persona companions | Why |

package/docs/guidelines/agent-infra/role-mode-router.md

@@ -62,11 +62,11 @@ both the number and the spelled-out slash command.
 ## Interactions
 
 - [`role-contracts`](role-contracts.md) — the contracts this router targets.
-- [`role-mode-adherence`](../../rules/role-mode-adherence.md) — enforces
+- [`role-mode-adherence`](../../../src/rules/role-mode-adherence.md) — enforces
   the contract once a mode is active.
-- [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — the
+- [`ask-when-uncertain`](../../../src/rules/ask-when-uncertain.md) — the
   fallback when no signal matches.
-- [`/mode`](../../commands/mode.md) — user-facing override.
+- [`/mode`](../../../src/domains/meta/mode/command.md) — user-facing override.
 
 ## Signal table maintenance
 

package/docs/guidelines/agent-infra/rule-type-governance.md

@@ -48,7 +48,7 @@ The `description` field IS the trigger. It must describe **when** the rule appli
 
 Every new rule, and every edited rule whose body changes the trigger
 or the obligation, MUST classify itself against the hardening tiers
-documented in [`rule-trigger-matrix.md`](../../agents/settings/contexts/rule-trigger-matrix.md):
+documented in [`rule-trigger-matrix.md`](../../../agents/settings/contexts/rule-trigger-matrix.md):
 
 | Tier | Meaning |
 |---|---|
@@ -64,7 +64,7 @@ Classification surface: the optional `tier:` frontmatter field
 rules; bulk-retrofit of existing rules is tracked separately.
 
 Tier 3 dispositions are recorded centrally in
-[`agents/settings/contexts/tier-3-dispositions.md`](../../agents/settings/contexts/tier-3-dispositions.md)
+[`agents/settings/contexts/tier-3-dispositions.md`](../../../agents/settings/contexts/tier-3-dispositions.md)
 with a 6-month re-audit clock. New Tier 3 rules append to that list
 on landing.
 

package/docs/guidelines/agent-infra/scqa-framework.md

@@ -17,16 +17,16 @@ refresh trigger.
 
 Cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../src/skills/deep-reading-analyst/SKILL.md)
   — Step 2B structural decomposition (always run, all depths).
-- [`agent-docs-writing`](../../../.agent-src.uncondensed/skills/agent-docs-writing/SKILL.md)
+- [`agent-docs-writing`](../../../src/skills/agent-docs-writing/SKILL.md)
   — narrative structure for module docs and AGENTS.md.
-- [`requesting-code-review`](../../../.agent-src.uncondensed/skills/requesting-code-review/SKILL.md)
+- [`requesting-code-review`](../../../src/skills/requesting-code-review/SKILL.md)
   — PR description structure (S = current state, C = pain point,
   Q = scope, A = the diff).
-- [`refine-prompt`](../../../.agent-src.uncondensed/skills/refine-prompt/SKILL.md)
+- [`refine-prompt`](../../../src/skills/refine-prompt/SKILL.md)
   — reconstruct a free-form prompt into S-C-Q-A acceptance criteria.
-- [`refine-ticket`](../../../.agent-src.uncondensed/skills/refine-ticket/SKILL.md)
+- [`refine-ticket`](../../../src/skills/refine-ticket/SKILL.md)
   — Jira / Linear ticket clarification through the four-element lens.
 
 > **The 4 elements:** S (Situation) · C (Complication) · Q (Question)

package/docs/guidelines/agent-infra/self-improvement-pipeline.md

@@ -28,7 +28,7 @@ blocks — it does not hand a half-filled doc to the next stage.
 
 - **Trigger:** a rule-worthy event. Bug pattern repeats, review
   finding recurs, a successful pattern is worth codifying.
-  The existing `capture-learnings` rule signals the event.
+  The existing `skill-improvement-trigger` rule signals the event.
 - **Input:** raw observation (PR link, log line, review comment).
 - **Output:** learning note at `agents/learnings/<date>-<slug>.md`
   with frontmatter `source`, `evidence[]` (≥1 link), `stage: captured`.
@@ -55,7 +55,7 @@ blocks — it does not hand a half-filled doc to the next stage.
 - **Input:** classified learning + any referenced existing artefact.
 - **Output:** proposal doc at
   `agents/proposals/<proposal_id>.md` following
-  [`proposal.example.md`](../../templates/agents/proposal.example.md).
+  [`proposal.example.md`](../../../src/agent-src/templates/agents/proposal.example.md).
   Frontmatter `stage: proposed`.
 - **Guardrails:** the draft body and the proposal doc are a single
   file. An artefact draft without its proposal wrapper is rejected.
@@ -99,7 +99,7 @@ blocks — it does not hand a half-filled doc to the next stage.
 
 | Stage | Human role | Automation |
 |---|---|---|
-| 1 Capture | Any contributor | `capture-learnings` rule auto-triggers |
+| 1 Capture | Any contributor | `skill-improvement-trigger` rule auto-triggers |
 | 2 Classify | Drafter | `learning-to-rule-or-skill` suggests |
 | 3 Propose | Drafter + reviewer | `skill-improvement-pipeline` refines |
 | 4 Gate | Gate script | fully automated, block is final |
@@ -129,6 +129,6 @@ unreviewed upstream changes is not.
 
 ## See also
 
-- [`proposal.example.md`](../../templates/agents/proposal.example.md) — the template every proposal derives from
-- [`artifact-drafting-protocol`](../../rules/artifact-drafting-protocol.md) — Understand → Research → Draft sequence used inside Stage 3
-- [`preservation-guard`](../../rules/preservation-guard.md) — invoked by the gate to check replacement proposals
+- [`proposal.example.md`](../../../src/agent-src/templates/agents/proposal.example.md) — the template every proposal derives from
+- [`artifact-drafting-protocol`](../../../src/rules/artifact-drafting-protocol.md) — Understand → Research → Draft sequence used inside Stage 3
+- [`preservation-guard`](../../../src/rules/preservation-guard.md) — invoked by the gate to check replacement proposals

package/docs/guidelines/agent-infra/simplicity-and-goal-demos.md

@@ -10,7 +10,7 @@ prose_delta:
 
 # Simplicity and Goal Discipline — wrong/right demos
 
-Recognition surface for [`minimal-safe-diff § Anti-over-engineering`](../../src/rules/minimal-safe-diff.md)
+Recognition surface for [`minimal-safe-diff § Anti-over-engineering`](../../../src/rules/minimal-safe-diff.md)
 (own-orphan cleanup, speculative-complexity bans) and the goal-driven
 execution clause in `think-before-action`. Per council convergence
 (2026-07-10): the demos ARE the enforcement — an agent that has never seen
@@ -166,7 +166,7 @@ pre-existing debt: mention it, don't delete it.
 
 The boundary is mechanical (grep after editing), so there is no
 judgment call to rationalize — see
-[`minimal-safe-diff § Own-orphan cleanup`](../../src/rules/minimal-safe-diff.md#own-orphan-cleanup).
+[`minimal-safe-diff § Own-orphan cleanup`](../../../src/rules/minimal-safe-diff.md#own-orphan-cleanup).
 
 ## Demo 6 — Vague plan vs. verifiable per-step plan
 

package/docs/guidelines/agent-infra/six-hats.md

@@ -7,12 +7,12 @@ separate thinking modes and avoid the cross-talk that derails group
 decisions. Adopted under the **Reference-Guideline Sunset Policy** and
 cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../src/skills/deep-reading-analyst/SKILL.md)
   — L2 Standard analysis depth (multi-perspective sweep).
-- [`ai-council`](../../../.agent-src.uncondensed/skills/ai-council/SKILL.md)
+- [`ai-council`](../../../src/skills/ai-council/SKILL.md)
   — multi-model consultation pattern; Six Hats is the per-perspective
   decomposition the council voices use when adjudicating a decision.
-- [`/council`](../../../.agent-src.uncondensed/commands/council.md)
+- [`/council`](../../../src/domains/meta/council/command.md)
   — internal council orchestrator routing to per-hat persona prompts.
 
 > **Core principle:** "Wear one hat at a time." — separating thinking

package/docs/guidelines/agent-infra/skill-quality-checklist.md

@@ -72,7 +72,7 @@ trigger-rich descriptions are required — polite or hedged ones cause
 undertriggering. The full recipe (concrete verb phrase, ≥2 triggers,
 `even if they don't explicitly ask for …` tail, ≤200 chars,
 litmus test) lives in
-[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../contexts/communication/rules-auto/skill-quality-mechanics.md)
+[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../../../src/agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md)
 § Description Triggering.
 
 ## Skill Independence
@@ -94,7 +94,7 @@ When merging or condensing skills, the result MUST preserve the
 strongest validation, strongest examples, all anti-patterns, all
 decision criteria, and trigger quality. Full preservation invariants
 and "merge is invalid if …" / "condensation may remove …" lists in
-[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../contexts/communication/rules-auto/skill-quality-mechanics.md)
+[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../../../src/agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md)
 § Merge Preservation and § Condensation Preservation.
 
 ## Refactor Safety
@@ -125,7 +125,7 @@ check. No retrofit pass on existing Wing-1 skills.
 
 Subsection specs (≤ 6-line spec + 1 reference example each), good /
 bad pattern pairs, and the WHEN-NOT routing peer rules live in
-[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../contexts/communication/rules-auto/skill-quality-mechanics.md)
+[`contexts/communication/rules-auto/skill-quality-mechanics.md`](../../../src/agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md)
 § Senior-tier patterns.
 
 ## Structural Malice Floor
@@ -139,10 +139,10 @@ linter exits with code **3** (security-failure), distinct from
 exit 2 (build-failure) so CI surfaces can split the two.
 
 The check is **structural**, not semantic — it catches the shapes
-the [`tool-safety`](tool-safety.md) rule denies in prose: hidden
+the [`tool-safety`](../../../src/rules/tool-safety.md) rule denies in prose: hidden
 credentials, arbitrary execution, write-without-approval. Fixtures
 and the exit-code-3 contract live in
-[`tests/test_skill_linter_malice.py`](../../tests/test_skill_linter_malice.py).
+[`tests/test_skill_linter_malice.py`](../../../tests/scripts/skill_linter.test.ts).
 
 ## Confidence Tagging
 
@@ -152,6 +152,6 @@ across steps. Optional but recommended when a step's output feeds a
 downstream decision.
 
 Text-tag form is deliberate. Emoji 🟢 / 🟡 / 🔴 is **not** allowed —
-collides with [`direct-answers`](direct-answers.md) § Emoji scope
+collides with [`direct-answers`](../../../src/rules/direct-answers.md) § Emoji scope
 (functional markers only). Linter does not enforce the tag itself;
 the rule documents the placement so authors converge on one form.

package/docs/guidelines/agent-infra/source-confidentiality-mechanics.md

@@ -0,0 +1,109 @@
+# Source confidentiality — mechanics
+
+Migrated out of [`source-confidentiality`](../../../src/rules/source-confidentiality.md)
+on 2026-08-29. The rule is delivered on **every subagent spawn**, so its body is
+paid per spawn; this material is reference read on demand. Nothing was dropped —
+the three sections below are the rule's own text, verbatim, and the rule keeps
+its Iron Laws and points here.
+
+### What "source-anonymous" claims, and what it explicitly does not
+
+```
+THE CLAIM IS ABOUT WHAT IS WRITTEN NEXT, NEVER ABOUT WHAT IS ALREADY RECORDED.
+NEVER DESCRIBE THIS AS ERADICATION, REMOVAL FROM HISTORY, OR A CLEAN REPOSITORY.
+COMMIT MESSAGES, MERGED PR BODIES AND OLD DIFFS REMAIN RECOVERABLE BY ANYONE
+WITH REPOSITORY ACCESS, AND NO PHASE OF THIS PROGRAMME CHANGES THAT.
+```
+
+The `whether-history-gets-rewritten` decision resolved **no rewrite** (AI
+council 2026-08-28, 2/2): the evidence estate rests on stable commit pins, and a
+`git filter-repo` would convert every past `reproduced at <sha>` into an
+unverifiable claim — a larger loss than the residual it removes, and one that
+would still not reach a pre-rewrite clone, a fork or a PR mirror. So the
+residual is **counted, not hidden**: the census artefact
+(`agents/evidence/reports/source-attribution-census.md`) carries a `residual:`
+field for the immutable surfaces, and "clean" always means "clean minus the
+recorded residual".
+
+### The two classes are opposites, and only one of them is a leak
+
+```
+HARVEST ATTRIBUTION IS PROHIBITED EVERYWHERE.
+LICENSE-REQUIRED ATTRIBUTION IS MANDATORY, AND LIVES ONLY IN THE LICENSE SURFACES.
+CONFLATING THEM IN EITHER DIRECTION IS A DEFECT: SCRUBBING A LICENSE NOTICE
+BREAKS A LEGAL OBLIGATION, AND HIDING A HARVEST BEHIND ONE IS THE LEAK.
+```
+
+The three license surfaces, by path — no others:
+
+- `CREDITS.md`
+- `docs/THIRD-PARTY-NOTICES.md`
+- `provenance/borrows.jsonl`
+
+An upstream name there is required by the license or by
+[`code-provenance`](code-provenance.md) and is never scrubbed. The same name in
+a roadmap, skill, rule, ADR or commit message is harvest attribution and is a
+defect. Every other `skip_paths` entry is a gate-own file or a vendored-cluster
+member carrying its own notice.
+
+## The gate also checks SHAPE, not only names
+
+A deny list can only catch a name somebody already wrote down; the next unknown
+source walks straight through it. `check_no_external_sources` therefore also
+flags attribution by **form** — a `> **Source:**` header whose value is neither
+an opaque round identifier nor an `ENC1:` token, a quoted
+`agents/tmp(.old)/<name>/` directory whose name is not opaque, and an
+un-allowlisted `github.com/<owner>/<repo>` URL — and it matches tracked **paths**
+against the deny set, not only file contents.
+
+Tiering, per the resolved `how-loud-the-slug-heuristic-is` decision (AI council
+2026-08-28, 2/2): **block inside `agents/**`, warn elsewhere** — slugs are
+ordinary content in integration code and docs, where blocking globally would
+drive the broad allowlisting that is worse than the gap it closes. The warn tier
+is written to a retained CI report (`--report <path>`), not merely printed, so
+it stays auditable. Pre-existing occurrences are a **shrink-only count** in
+`src/config/gate-violation-baselines.json`, never an allowlist: nothing is
+excused and a new occurrence fails immediately.
+
+## Why these four rules are unconditional
+
+Under ADR-236 (`docs/decisions/ADR-236-one-artefact-one-layer.md`) this rule is
+delivered by the PROJECT layer only — it exists to maintain this package, so the
+global layer no longer carries an unscoped twin of it. A `paths:`-scoped rule is
+**not re-injected after `/compact`** (ADR-227:79-80), so scoping it would mean the
+obligation silently disappears mid-session with nothing left to reload it.
+
+It is therefore delivered unconditionally, and the path triggers were removed
+rather than worked around. **This section is the shared record for all four such
+rules** — `no-roadmap-references`, `rule-type-governance` and `skill-quality` carry
+the same change and no note of their own. Two reasons: four copies of the rationale
+cost more standing context than the decision they explain, and the other three are
+migrated POINTER stubs held at their pointer's size by
+`check_rule_stub_ceiling` — prose added there is prose in the wrong place by that
+gate's own contract, which is what caught the first attempt to duplicate it.
+
+AI council 2026-08-20, 2/2 convergent on this option over three alternatives, with
+two independent decisive arguments. First: the obligation governs an **authoring
+decision**, which happens before any file exists for a path trigger to match — so
+path-scoping fails at greenfield creation whether or not a compaction ever occurs.
+Second: the measured cost is small against what the partition returns. Keeping an
+unscoped global copy was rejected because it re-creates the duplication the
+partition exists to remove; splitting the four by "has a CI gate" was rejected by
+both seats as the wrong axis — a validator observes an outcome, it does not hold an
+obligation during the session, and `rule-type-governance` has no gate at all.
+
+**Cost, measured and corrected.** An earlier revision of this note claimed 1,754
+tokens (1.8 % of the partition's 96,584-token saving). That figure was a
+`chars / 4` proxy over the projected files and **understated the real cost by about
+half**: `check_rule_activation_census`, which counts with the exact BPE tokenizer,
+measures the unconditional corpus growing **108,130 → 111,642, i.e. +3,512 tokens
+(3.6 %)** — and that number includes this rationale, which is why it lives in one
+place instead of four. The verdict does not depend on the figure: one seat argued
+the token axis was the wrong one entirely, the other that cost is a legitimate axis
+which simply loses this particular comparison. Both readings survive 3.6 %.
+
+## See also
+
+- [`source-confidentiality`](../../../src/rules/source-confidentiality.md) — the rule these mechanics belong to.
+- [`code-provenance`](../../../src/rules/code-provenance.md) — the license-required-attribution obligation the two-class split defers to.
+- `src/scripts/check_no_external_sources.ts` — the gate that implements the shape checks.

package/docs/guidelines/agent-infra/systems-thinking.md

@@ -7,7 +7,7 @@ feedback loops, leverage points, and cross-domain archetypes that
 reveal where intervention has the highest impact. Adopted under the
 **Reference-Guideline Sunset Policy** and cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../src/skills/deep-reading-analyst/SKILL.md)
   — L3 Deep analysis depth.
 - [`mental-models`](mental-models.md) — Munger's lattice; systems
   thinking is one of the strongest engineering / biology lenses.

package/docs/guidelines/agent-infra/verify-before-complete-demos.md

@@ -13,9 +13,9 @@ prose_delta:
 > Wrong / right / why demos for the `verify-before-complete` Iron
 > Law (no completion claim without fresh evidence in this message).
 > Linked from
-> [`verify-before-complete`](../../.agent-src.uncondensed/rules/verify-before-complete.md)
+> [`verify-before-complete`](../../../src/rules/verify-before-complete.md)
 > § Examples. Outcome baseline at
-> [`tests/golden/outcomes/verify_before_complete.json`](../../tests/golden/outcomes/verify_before_complete.json).
+> [`tests/golden/outcomes/verify_before_complete.json`](../../../tests/golden/outcomes/verify_before_complete.json).
 
 ## Demo 1 — Hedged completion claim
 

package/docs/guidelines/augment-portability-patterns.md

@@ -54,10 +54,12 @@ installer, gitignored). Artefacts MUST prefer the CLI over raw
 
 The full `task`-to-script translation table, the `./agent-config`
 CLI mapping, and the rationale (Task absence on consumers,
-maintainer-vs-artefact split) all live in
-[`contexts/communication/rules-auto/augment-portability-mechanics.md`](../contexts/communication/rules-auto/augment-portability-mechanics.md).
-Pull it whenever an artefact is about to mention a runtime
-invocation.
+maintainer-vs-artefact split) are **in this file**.
+
+> **Corrected 2026-08-26** (`road-to-contract-review-deadlines` 4.2): this
+> paragraph used to point at a `rules-auto` mechanics file under the contexts
+> tree, which exists nowhere in it. The pointer described a split that was never
+> made; the material it names was already here.
 
 ## Enforcement
 

package/docs/guidelines/code-clarity.md

@@ -315,6 +315,24 @@ Behavioral baseline: `tests/code-comments/eval-fixtures.md`
 `ccd-untouched-preservation`, `ccd-explicit-teaching-override`); the decidable
 criteria are proven by `tests/scripts/code_comment_fixtures.test.ts`.
 
+### Evidence belongs in the roadmap that asked for it
+
+Measured 2026-09-02 in a consumer repository: **509 German comment lines** and
+**21 report- or provenance-shaped comments** across **41 of 45** changed source
+files, the worst a 101-line colour-analysis report inside a CSS file. The cause
+was a roadmap requiring proof for every checked step: the run read that as
+*evidence should be documented* and wrote the measurements into the source too,
+where the roadmap already carried them.
+
+The provenance of a value is not a WHY, and a roadmap cannot license a comment
+the rule forbids.
+
+Two enforcers carry this because neither rule could fire on a write:
+`code-comment-discipline` matches prompt keywords, and `language-and-tone`'s
+English-comment clause named a `.md`-only validator. `lint_code_comments`
+refuses on the diff; the `comment-discipline` concern reports on the text as
+written. Neither replaces the discipline.
+
 ## See also
 
 - Language-specific anchors that link to this guideline:

package/docs/guidelines/component-oriented-and-oop-development.md

@@ -129,8 +129,9 @@ compose don't duplicate) is paradigm-independent; only its *shape* is OO here:
 
 Language / framework carve-outs (never restated here): PHP →
 [`php-coding-patterns`](php/php-coding-patterns.md) +
-[`patterns.md`](php/patterns.md) (+ `patterns/strategy.md`,
-`patterns/dependency-injection.md`, `patterns/factory.md`, `patterns/service-layer.md`)
+[`patterns.md`](php/patterns.md) (+ `php/patterns/strategy.md`,
+`php/patterns/dependency-injection.md`, `php/patterns/factory.md`,
+`php/patterns/service-layer.md`)
 + skills [`php-coder`](../../src/skills/php-coder/SKILL.md) /
 [`php-service`](../../src/skills/php-service/SKILL.md); Laravel →
 [`laravel`](../../src/skills/laravel/SKILL.md); Symfony →

package/docs/guidelines/cross-role-handoff.md

@@ -93,7 +93,7 @@ Council Q3 (2026-05-05) locks the disambiguation between L4
   shipping — becomes **input to L4**. The escalation is one-way:
   L4 produces the dissent log that decides whether C8's verdict
   is overridden, with the override recorded in
-  [`decision-record`](../../.agent-src.uncondensed/skills/decision-record/SKILL.md).
+  [`decision-record`](../../src/skills/decision-record/SKILL.md).
 
 The boundary keeps the two skills sharp — neither absorbs the other —
 and gives the agent a deterministic rule for which one to load when
@@ -108,7 +108,7 @@ acquisition channel is paid search, but only if CAC payback < 6 months"*:
 2. The CAC question is Wing-4 cognition — `unit-economics-modeling`.
 3. `refine-ticket` hands off via:
    - WHEN NOT entry: *"CAC / payback questions — route to
-     [`unit-economics-modeling`](../unit-economics-modeling/SKILL.md)"*.
+     [`unit-economics-modeling`](../../src/skills/unit-economics-modeling/SKILL.md)"*.
    - Composes line in the procedure step that needs the answer.
 4. The delegate's `## Input` block lists the fields (channel,
    cohort, time horizon); `refine-ticket` passes them.

package/docs/guidelines/design-fidelity-mechanics.md

@@ -161,7 +161,7 @@ The Iron Law and both discriminator clauses stay in
 
 | The artefact declares | The spec is | The spec is NOT |
 |---|---|---|
-| low fidelity — greyscale, box-and-line, placeholder copy | layout · element set · hierarchy · states shown | greys · placeholder text · borders · exact spacing |
+| low fidelity — greyscale, box-and-line, placeholder copy | layout · element set · hierarchy · states shown | grays · placeholder text · borders · exact spacing |
 | finished — colour, real copy, real assets | everything visible (the 1:1 floor, unchanged) | — |
 
 Grounded in [`wireframe`](../../src/skills/wireframe/SKILL.md) § Gotchas. The near-miss

package/docs/guidelines/docs/readme-size-and-splitting.md

@@ -38,9 +38,9 @@ Hard triggers — split immediately:
   deep links
 - **More than 3 framework adapters** → each adapter gets its own doc
 - **Architecture or design rationale > 30 lines** → `docs/architecture.md`
-- **API reference > 50 lines** → `docs/api.md` or auto-generated reference
+- **API reference > 50 lines** → `docs/api.md` or auto-generated reference <!-- ref-ignore -->
 - **Multiple audiences with different needs** → audience-specific docs
-  (`docs/consumers.md`, `docs/contributors.md`)
+  (`docs/consumers.md`, `docs/contributors.md`) <!-- ref-ignore -->
 
 Soft triggers — review and probably split:
 
@@ -122,7 +122,7 @@ deep-link the other:
 - **Package repo** → consumers primary; contributors go to
   `CONTRIBUTING.md` or `docs/development.md`
 - **Application repo** → contributors/team primary; end users (if any)
-  go to `docs/user-guide.md`
+  go to `docs/user-guide.md` <!-- ref-ignore -->
 
 The README must declare its audience within the first screen. Readers
 in the other audience must find their link within the first screen too.