@event4u/agent-config 14.12.0 → 14.14.0

package/docs/contracts/settings-classes.md

@@ -1,3 +1,8 @@
+---
+stability: beta
+keep-beta-until: 2026-11-24
+---
+
 # Settings classes — A / B / C
 
 > Every leaf key in `src/config/agent-settings.template.yml` carries exactly one
@@ -242,8 +247,8 @@ dispatch runs, not WHETHER the layer exists, so they keep their own C rows.
 |---|---|
 | A — preference | 26 |
 | B — consent | 3 |
-| C — guarded | 109 |
-| **Total** | **138** |
+| C — guarded | 110 |
+| **Total** | **139** |
 
 The total was 140 until 2026-08-12, when five of the six keys no code path read were
 deleted, minus the one held open (§ The six unread keys, below): one A
@@ -333,9 +338,9 @@ the template, which is the drift this contract exists to prevent.
 |---|---|
 | derivable | 83 |
 | un-inferrable | 9 |
-| consent | 40 |
+| consent | 41 |
 | policy | 6 |
-| **Total** | **138** |
+| **Total** | **139** |
 
 First measured 2026-08-12 at 140 leaves (derivable 88 · consent 38 ·
 un-inferrable 9 · policy 5), from the table below rather than predicted — the
@@ -550,6 +555,7 @@ Rows follow template order, so a diff against the template reads straight down.
 | `hooks.injection_scan.enabled` | C | `false` | the prompt-injection scanner | derivable — the scanner's own signature match on the tool envelope; warn-only and silent on no hit |
 | `hooks.rtk_wrap.enabled` | C | `false` | configures code that runs on every tool call | derivable — the live PATH and identity probe the hook already runs; silent when rtk is absent |
 | `hooks.design_slop.enabled` | C | `false` | configures code that runs on every tool call | derivable — the rule-registry match plus the hook's own per-signature silence cap |
+| `hooks.runtime_journal.enabled` | C | `false` | configures code that runs on every dispatched hook event | consent |
 | `hooks.ui_route_nudge.enabled` | C | `false` | configures code that runs on every tool call | derivable — the UI-surface predicate plus the hook's own two-nudges-per-session cap |
 | `hooks.design_pass.enabled` | C | `false` | C-test 1 — it configures code that runs on every tool call and at every turn end, and unlike its two `hooks.*` neighbours its stop pass can BLOCK rather than warn | policy — whether an operator accepts a gate that can refuse a turn is a risk preference, not a fact the tree can compute. The two neighbours are `derivable` because they only ever warn; the block is the discriminator. `road-to-frontend-power` transfers the default flip to the owner for the same reason |
 | `hooks.code_graph.enabled` | C | `false` | configures code that runs on every tool call | derivable — the index-detection probe the nudge already runs; no index means silence |

package/docs/guidelines/agent-infra/5w2h-analysis.md

@@ -6,11 +6,11 @@ comprehensive understanding of any topic, problem, or plan. Adopted under
 the **Reference-Guideline Sunset Policy** (see frontmatter `upstream` /
 `refresh_trigger` keys) 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)
   — L1 Quick analysis depth.
-- [`refine-ticket`](../../../.agent-src.uncondensed/skills/refine-ticket/SKILL.md)
+- [`refine-ticket`](../../../src/skills/refine-ticket/SKILL.md)
   — completeness check on a Jira / Linear ticket before estimation.
-- [`bug-investigate`](../../../.agent-src.uncondensed/commands/bug/investigate.md)
+- [`bug-investigate`](../../../src/domains/engineering-base/bug/investigate/command.md)
   — gap analysis on an incident report before forming a hypothesis.
 
 > **Core principle:** "Quality of decisions equals quality of questions

package/docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md

@@ -266,6 +266,7 @@ is a pairwise contract scoped to the always-on kernel rules — forking that
 linted contract with a second prose ordering over a different kind of object is
 the drift this ladder exists to avoid.
 
+
 ### 8c. Is the approach sound?
 
 - Is there a simpler way to achieve the same result?

package/docs/guidelines/agent-infra/artifact-drafting-protocol-mechanics.md

@@ -57,6 +57,61 @@ and let the user re-decide.
 Carry the summary into the commit message (*"Reviewed before drafting:
 X, Y"*).
 
+### Where the answer is written — `composition_review:`
+
+A commit message is not a tree artifact. Measured 2026-08-27 over the twenty most
+recently added skills and rules
+(`agents/evidence/analysis/authoring-search-record-sample-2026-08-27.md`), **1 of
+20** carried a machine-readable record of the Phase-B verdict; 9 carried a strict
+prose one, and the rest carried a `See also` gloss or a routing row. So an
+artifact authored after a thorough scan and one authored after none were
+indiscernible in the tree — which is why the overlap tools
+(`audit_overlap`, `audit_skill_overlap`, `report_layer_overlap`) run over a
+corpus rather than over a decision.
+
+The record is a frontmatter block, defined in `skill.schema.json` and
+`rule.schema.json`, and **optional on existing artifacts by design — nothing is
+backfilled**:
+
+```yaml
+composition_review:
+  - candidate: skill:existing-ui-audit      # skill: / rule: / command: / guideline: / none
+    disposition: create_separate            # what happened to this candidate
+    rationale: audits what exists before a write; this governs the write itself
+```
+
+Four dispositions, and the discriminator for each:
+
+| Value | Means |
+|---|---|
+| `extend_incumbent` | the incumbent absorbed the change; no new artifact was created |
+| `compose_with_incumbent` | the new artifact routes to the incumbent rather than restating it |
+| `create_separate` | the incumbent exists, was evaluated, and a separate artifact was authored anyway |
+| `none_found` | the search ran and found no credible incumbent — pairs only with `candidate: none` |
+
+`none_found` exists so an author is never pushed to **invent** an incumbent to
+satisfy the schema. That failure would manufacture the pro-forma record the
+mechanism is supposed to measure, using the mechanism.
+
+`create_separate` is the value no other disposition vocabulary in this tree can
+express, and it is why this is a fifth enum rather than a reuse. The nearest
+incumbent is the harvest ledger's `adopt | adapt`
+(`lint_harvest_provenance.ts:76`), which deliberately **excludes** rejection
+(`:222`) because a rejected harvest has no artifact to cite. This record is the
+mirror image — it is written *on* the artifact being created — so rejection is
+the value it most needs. The finding, review and archive vocabularies are about
+defects, review rows and roadmap files respectively; none of them has a slot for
+"an incumbent existed and I built anyway".
+
+**What the lint does and does not do.** `lint_composition_review` fails a record
+whose `candidate` resolves to no artifact, or whose `none` / `none_found` pair
+disagrees — a record naming an incumbent that is not in the tree reads as
+evidence of a search that cannot have happened. It *reports without failing* an
+addition carrying no record at all. It cannot check that the search happened,
+that the rationale is true, or that the named incumbent is the nearest one;
+flipping the advisory half to a block needs a false-positive rate from at least
+one release of advisory operation, which does not exist yet.
+
 ## Phase C — Draft
 
 Propose **2-3 description variants** — Conservative / Pushy
@@ -135,7 +190,7 @@ that lives only in the roadmap that flipped the default becomes unreachable
 the moment that roadmap is archived.
 
 
-## Complexity budget — the six questions before a new artefact
+## Complexity budget — the six questions before a new artifact
 
 Folded here from the 9.4.0 review (Prio 5), which named the failure mode:
 "das Paket kann fast jede Kritik mit einem weiteren Mechanismus beantworten"
@@ -144,12 +199,12 @@ inflation). This REPLACES the ad-hoc "should this exist" prose — it is a
 checklist, not a new gate/rule (adding a gate to enforce "add less" would be
 the very inflation it guards against). Before drafting any new skill / rule /
 command / hook / gate, answer all six; a "no" on **replaces** or **removable**
-is a strong signal to fold into an existing artefact instead:
+is a strong signal to fold into an existing artifact instead:
 
 1. **Replaces?** — what existing mechanism does this retire or subsume? (If
    nothing, justify why the surface must grow.)
 2. **Overlaps?** — does it duplicate a trigger / responsibility another
-   artefact already owns?
+   artifact already owns?
 3. **Discoverable?** — will a user actually find it, or does it just raise the
    catalog count?
 4. **Measurable?** — is there a signal that would show it earning its place

package/docs/guidelines/agent-infra/ask-when-uncertain-demos.md

@@ -12,9 +12,9 @@ prose_delta:
 
 > Wrong / right / why demos for the `ask-when-uncertain` Iron Law
 > (one question per turn, vague-request must ask). Linked from
-> [`ask-when-uncertain`](../../.agent-src.uncondensed/rules/ask-when-uncertain.md)
+> [`ask-when-uncertain`](../../../src/rules/ask-when-uncertain.md)
 > § Examples. Outcome baseline at
-> [`tests/golden/outcomes/ask_when_uncertain.json`](../../tests/golden/outcomes/ask_when_uncertain.json).
+> [`tests/golden/outcomes/ask_when_uncertain.json`](../../../tests/golden/outcomes/ask_when_uncertain.json).
 
 ## Demo 1 — Vague request, multi-question stack
 

package/docs/guidelines/agent-infra/asking-and-brevity-examples.md

@@ -1,9 +1,9 @@
 # asking-and-brevity-examples
 
 Companion examples for three always-rules:
-[`ask-when-uncertain`](../../../.agent-src.uncondensed/rules/ask-when-uncertain.md),
-[`no-cheap-questions`](../../../.agent-src.uncondensed/rules/no-cheap-questions.md),
-[`direct-answers`](../../../.agent-src.uncondensed/rules/direct-answers.md).
+[`ask-when-uncertain`](../../../src/rules/ask-when-uncertain.md),
+[`no-cheap-questions`](../../../src/rules/no-cheap-questions.md),
+[`direct-answers`](../../../src/rules/direct-answers.md).
 
 The rules carry the Iron Laws and the obligation surface. This file
 carries the illustrative material (example questions, rationale

package/docs/guidelines/agent-infra/break-glass-usage.md

@@ -56,14 +56,14 @@ reproducer to the follow-up ticket.
 
 These rules stay fully in force, break-glass or not:
 
-- [`minimal-safe-diff`](../../rules/minimal-safe-diff.md) — the hotfix is
+- [`minimal-safe-diff`](../../../src/rules/minimal-safe-diff.md) — the hotfix is
   still the **smallest** change that stops the bleeding. No drive-by
   cleanups.
-- [`security-sensitive-stop`](../../rules/security-sensitive-stop.md) — a
+- [`security-sensitive-stop`](../../../src/rules/security-sensitive-stop.md) — a
   security-relevant change still needs the threat-model pass.
-- [`scope-control`](../../rules/scope-control.md) — never mix the
+- [`scope-control`](../../../src/rules/scope-control.md) — never mix the
   hotfix with unrelated refactors from another branch.
-- [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — more
+- [`ask-when-uncertain`](../../../src/rules/ask-when-uncertain.md) — more
   asking, not less, when the blast radius is live.
 
 ## Required artifacts
@@ -104,10 +104,10 @@ Within 24 hours:
 
 ## See also
 
-- [`minimal-safe-diff`](../../rules/minimal-safe-diff.md) — break-glass
+- [`minimal-safe-diff`](../../../src/rules/minimal-safe-diff.md) — break-glass
   exception section.
-- [`verify-before-complete`](../../rules/verify-before-complete.md) —
+- [`verify-before-complete`](../../../src/rules/verify-before-complete.md) —
   break-glass reduction section.
-- [`security-sensitive-stop`](../../rules/security-sensitive-stop.md).
+- [`security-sensitive-stop`](../../../src/rules/security-sensitive-stop.md).
 - [`review-routing-data-format`](review-routing-data-format.md) —
   where to register newly-discovered failure modes.

package/docs/guidelines/agent-infra/carve-out-predicates.md

@@ -1,14 +1,14 @@
 # Decidable Carve-Out Predicates
 
-Companion to [`frugality-charter`](../../../.agent-src.uncondensed/contexts/contracts/frugality-charter.md). Each carve-out below carries a one-sentence test. If the test cannot be answered yes/no from the artifact alone, the carve-out does not fire and default-terse rules apply.
+Companion to [`frugality-charter`](../../../src/agent-src/contexts/contracts/frugality-charter.md). Each carve-out below carries a one-sentence test. If the test cannot be answered yes/no from the artifact alone, the carve-out does not fire and default-terse rules apply.
 
 ## Predicates
 
 - **Iron-Law literal** — the prose is an ALL-CAPS fenced block inside a rule whose title appears in [`docs/contracts/kernel-membership.md`](../../contracts/kernel-membership.md).
 
-- **Numbered-options with genuine trade-off** — the options differ in consequence (a chosen path produces a measurably different artifact or state), not in sequencing or output format. Per [`no-cheap-questions § What counts as cheap`](../../../.agent-src.uncondensed/rules/no-cheap-questions.md#what-counts-as-cheap).
+- **Numbered-options with genuine trade-off** — the options differ in consequence (a chosen path produces a measurably different artifact or state), not in sequencing or output format. Per [`no-cheap-questions § What counts as cheap`](../../../src/rules/no-cheap-questions.md#what-counts-as-cheap).
 
-- **Security-sensitive prompt** — the prompt requires credential input OR modifies auth / tenant / secret state, matching a trigger in [`security-sensitive-stop`](../../../.agent-src.uncondensed/rules/security-sensitive-stop.md).
+- **Security-sensitive prompt** — the prompt requires credential input OR modifies auth / tenant / secret state, matching a trigger in [`security-sensitive-stop`](../../../src/rules/security-sensitive-stop.md).
 
 - **Structured CLI contract** — the script's stdout is consumed by another script (a downstream parser exists under `scripts/` or `.augment/scripts/`), so the format is part of an interface contract, not narration.
 

package/docs/guidelines/agent-infra/comparison-matrix.md

@@ -7,7 +7,7 @@ quality, and viewpoints to synthesize an integrated understanding rather
 than a stack of independent summaries. 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)
   — L4 Research analysis depth (web-search 2–3 related sources, compare,
   synthesize).
 - [`critical-thinking`](critical-thinking.md) — per-source argument

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

@@ -8,13 +8,13 @@ rebuilds from primitives) and `inversion-thinking` (which negates the
 goal). 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 / L3 Deep evaluation depth.
-- [`receiving-code-review`](../../../.agent-src.uncondensed/skills/receiving-code-review/SKILL.md)
+- [`receiving-code-review`](../../../src/skills/receiving-code-review/SKILL.md)
   — steelman bot / human review feedback before changing code.
-- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../src/rules/improve-before-implement.md)
   — challenge weak requirements with evidence-grade analysis.
-- [`adversarial-review`](../../../.agent-src.uncondensed/skills/adversarial-review/SKILL.md)
+- [`adversarial-review`](../../../src/skills/adversarial-review/SKILL.md)
   — paired stress-test on a diff after critique.
 
 > **Core principle:** "Steelman first, criticize second." — attacking

package/docs/guidelines/agent-infra/direct-answers-demos.md

@@ -13,9 +13,9 @@ prose_delta:
 > Wrong / right / why demos for the three Iron Laws of
 > `direct-answers` (no flattery, no invented facts, brevity by
 > default). Linked from
-> [`direct-answers`](../../.agent-src.uncondensed/rules/direct-answers.md)
+> [`direct-answers`](../../../src/rules/direct-answers.md)
 > § Examples. Outcome baseline at
-> [`tests/golden/outcomes/direct_answers.json`](../../tests/golden/outcomes/direct_answers.json).
+> [`tests/golden/outcomes/direct_answers.json`](../../../tests/golden/outcomes/direct_answers.json).
 
 ## Demo 1 — Flattery opener (Iron Law 1)
 

package/docs/guidelines/agent-infra/domain-eval-anti-pattern.md

@@ -50,4 +50,4 @@ A false structural blocker is as much an error as false objectivity.
 
 - [ADR-107 — Legal domain-pack adoption](../../decisions/ADR-107-legal-domain-pack-adoption.md)
 - `domain-pack-architecture.md` — the retrospective sequence this is part of.
-- `src/domains/legal/evals/README.md` — the regression harness in practice.
+- `src/domains/legal-review-prep/evals/README.md` — the regression harness in practice.

package/docs/guidelines/agent-infra/engineering-memory-data-format.md

@@ -123,12 +123,12 @@ is not a forensic record.
 Each file also carries the template-specific body. See the example
 templates for the full shape:
 
-- [`domain-invariants.example.yml`](../../templates/agents/memory/domain-invariants.example.yml)
+- [`domain-invariants.example.yml`](../../../src/agent-src/templates/agents/memory/domain-invariants.example.yml)
   adds `rule`, `boundary`, `scope.paths`, `violation_contract`.
-- [`incident-learnings.example.yml`](../../templates/agents/memory/incident-learnings.example.yml)
+- [`incident-learnings.example.yml`](../../../src/agent-src/templates/agents/memory/incident-learnings.example.yml)
   adds `pattern`, `trigger_conditions`, `consequence`, `guardrail`,
   `enforcement`, `severity`.
-- [`product-rules.example.yml`](../../templates/agents/memory/product-rules.example.yml)
+- [`product-rules.example.yml`](../../../src/agent-src/templates/agents/memory/product-rules.example.yml)
   adds `rule`, `applies_to`, `enforcement`, `error_contract`, `version`.
 
 ## Ownership (who writes, who reads)

package/docs/guidelines/agent-infra/existence-question-verdicts.md

@@ -0,0 +1,80 @@
+# The existence question — its verdict set, its cost, and why it is not TDD
+
+Depth for [`improve-before-implement`](../../../src/rules/improve-before-implement.md)
+§ The solution-size ladder, migrated out of
+[`agent-interaction-and-decision-quality`](agent-interaction-and-decision-quality.md)
+§ 8b.
+
+**Why it moved.** That guideline crossed `check_depth_budget`'s 16,000-character
+ceiling when this depth landed in it, becoming a fifth over-ceiling file against
+a baseline of four. The ratchet turns one way, so the fix is extraction rather
+than a raised baseline — and these three sections are the natural unit: they
+answer what the ladder RETURNS, what it costs, and which cluster it does not
+belong to, none of which the surrounding interaction guideline needs in order to
+be read.
+
+The ladder itself — the rungs, the shape axis and their precedence — stays at
+§ 8b-ladder / 8b-shape / 8b-precedence, because the rule routes there.
+
+#### 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 behaviour 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/first-principles.md

@@ -8,11 +8,11 @@ verified primitives and reconstruct it without inherited convention.
 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; first
   principles is the foundational physics-style lens.
-- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../src/rules/improve-before-implement.md)
   — challenge the framing of a request before coding it.
 - [`inversion-thinking`](inversion-thinking.md) — pair: first
   principles rebuilds; inversion stress-tests the rebuild.

package/docs/guidelines/agent-infra/framework-neutrality-patterns.md

@@ -41,8 +41,8 @@ A generic artifact may end a section with a one-line handoff to its
 framework-specific peers. Canonical shape:
 
 ```
-→ Laravel-specific: see [laravel-validation](../skills/laravel-validation/SKILL.md)
-→ Next.js-specific: see [nextjs-patterns](../skills/nextjs-patterns/SKILL.md)
+→ Laravel-specific: see [laravel-validation](../../../src/skills/laravel-validation/SKILL.md)
+→ Next.js-specific: see [nextjs-patterns](../../../src/skills/nextjs-patterns/SKILL.md)
 ```
 
 The pointer is a link, not a procedure — the generic artifact never

package/docs/guidelines/agent-infra/guarded-baseline.md

@@ -0,0 +1,39 @@
+# `guarded-baseline` — a sub-state of `[ ]`, never a fifth glyph
+
+> Migrated out of [`roadmap-progress-mechanics`](roadmap-progress-mechanics.md)
+> on 2026-08-31, on arrival: that file measured 15,873 of the 16,000-char
+> depth ceiling, leaving 127 characters, so the section could not live there.
+> The ceiling is a growth ratchet, and hitting it is the signal to split rather
+> than to raise it. The glyph-semantics table there points here.
+
+A step whose `verify:` asserts a property of a mechanism that **does not yet exist** may not close `[x]`: an executable guard proven to go RED under a named sabotage is evidence about the *guard*, not about the *absent mechanism*, and `[x]` would claim the acceptance criterion was satisfied. Such a step keeps its `[ ]` box and carries an annotation plus a structured evidence record (AI council 2026-08-31, 2/2 convergent — `anthropic/claude-sonnet-4-5` + `openai/codex-default`, option C):
+
+~~~md
+- [ ] <!-- roadmap-status: guarded-baseline -->
+      **12.1** …step text…
+      ```yaml
+      guarded_baseline:
+        category: future-mechanism   # or absence-assertion — no other value
+        scope: <surfaces examined>
+        command: <reproducible green command>
+        red_proof: <commit, fixture, or recorded sabotage run>
+        sabotage_model: <exact violation introduced>
+        recheck_when: <mechanism / symbol / path trigger>
+        discharged_ac: <clauses actually completed>
+        pending_ac: <clauses still unexercisable>
+      ```
+~~~
+
+The two categories are the discriminator, not decoration. An **`absence-assertion`** step asserts something directly observable today ("the schema has no field capable of holding prompt text") and MAY close `[x]` once sabotage-verified. A **`future-mechanism`** step asserts a property of something that does not exist ("a probe-resolvable fixture never enters the selector") and is what this sub-state exists for. No third value is accepted, and an absent `category` is a rejection rather than a default.
+
+Tooling, all of it in `guarded_baseline.ts` and enforced by both consumers:
+
+| Behavior | Where |
+|---|---|
+| Counted as **open**, never as done — the canonical box stays `[ ]` | `count_checkboxes` |
+| Reported **separately**: a `## 🛡️ Guarded baselines` dashboard section plus a per-step stderr line | `update_roadmap_progress` |
+| **Rejected** — exit 1, on both `--check` and a plain regen — when `red_proof` is absent, when `category` is absent or illegal, when there is no evidence block, or when the annotation sits on anything but `- [ ]` | `update_roadmap_progress` |
+| Treated as **incomplete**: archival refused and the reason named | `archive_completed_roadmaps` |
+| Marked **stale** once a path-shaped `recheck_when` trigger resolves in the tree. A trigger carrying **no** path token at all is reported as not machine-checkable rather than as not-stale; a trigger carrying at least one path token is decided by that path and is **not** reported, even when a companion symbol token sits beside it — a checked trigger that looks unchecked is the mirror of the failure the report exists to prevent (measured 2026-09-01: 3 of 4 reported lines were already decidable) | `guardedBaselineStaleness` |
+
+Only verification against the real mechanism permits `[x]`. **A baseline that has not demonstrably gone RED is an ordinary open item** and must not carry the annotation at all — the sabotage-and-restore proof is the entry price, not a nice-to-have.

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

@@ -4,18 +4,18 @@ Reference guideline for Wing-1 deep-thinking work — Carl Jacobi's
 "invert, always invert" applied to **decisions and arguments**, not
 diffs. The pre-mortem on a strategy, an argument, or a written plan;
 distinct from
-[`adversarial-review`](../../../.agent-src.uncondensed/skills/adversarial-review/SKILL.md)
+[`adversarial-review`](../../../src/skills/adversarial-review/SKILL.md)
 which stress-tests **diffs**. Adopted under the **Reference-Guideline
 Sunset Policy** (see frontmatter `upstream` / `refresh_trigger` keys)
 and cross-referenced from:
 
-- [`refine-prompt`](../../../.agent-src.uncondensed/skills/refine-prompt/SKILL.md)
+- [`refine-prompt`](../../../src/skills/refine-prompt/SKILL.md)
   — pre-mortem on a free-form prompt before planning.
-- [`refine-ticket`](../../../.agent-src.uncondensed/skills/refine-ticket/SKILL.md)
+- [`refine-ticket`](../../../src/skills/refine-ticket/SKILL.md)
   — pre-mortem on a Jira / Linear ticket before estimation.
-- [`threat-modeling`](../../../.agent-src.uncondensed/skills/threat-modeling/SKILL.md)
+- [`threat-modeling`](../../../src/skills/threat-modeling/SKILL.md)
   — abuse-case generation pairs with goal inversion.
-- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../src/rules/improve-before-implement.md)
   — challenge weak requirements before writing code.
 
 > **Core principle:** "Invert, always invert." — Carl Jacobi

package/docs/guidelines/agent-infra/language-and-tone-examples.md

@@ -1,6 +1,6 @@
 # language-and-tone — examples and failure modes
 
-> Reference companion to [`dist/agent-src/rules/language-and-tone.md`](../../dist/agent-src/rules/language-and-tone.md).
+> Reference companion to [`dist/agent-src/rules/language-and-tone.md`](../../../src/rules/language-and-tone.md).
 > Pulled out so the always-active rule stays under its character budget.
 > Linked from the rule via the **Examples** section; agents do not load this file
 > automatically, only when they want concrete demonstrations or are debugging a

package/docs/guidelines/agent-infra/layered-settings.md

@@ -19,18 +19,18 @@ on user request.
 |---|---|---|---|---|
 | `.agent-project-settings.yml` | **committed** | team / repo | lead maintainer | `project.stack`, `quality.php.tools`, `memory.dogfood` |
 | `~/.event4u/agent-config/agent-settings.yml` | **n/a** (outside repo) | individual developer · cross-project | individual | `name`, `ide`, `rule_loading_tier`, `personal.bot_icon`, `personal.autonomy`, `memory.cadence` (legacy `~/.config/agent-config/agent-settings.yml` read as fallback) |
-| `agents/settings/.agent-settings.yml` | **gitignored** | individual developer · this project | individual | `personal.ide`, `personal.user_name`, `subagents.max_parallel`, `onboarding.onboarded` |
+| `agents/settings/.agent-settings.yml` | **gitignored** | individual developer · this project | individual | `personal.ide`, `personal.user_name`, `subagents.max_parallel`, `onboarding.onboarded` | <!-- ref-ignore -->
 
 > **Canonical location (ADR-038):** the developer file lives in the settings
-> layer at `agents/settings/.agent-settings.yml` (alongside
+> layer at `agents/settings/.agent-settings.yml` (alongside <!-- ref-ignore -->
 > `.agent-settings.local.yml`, `contexts/`, `policies/`). A repo-root
 > `.agent-settings.yml` is read as a **back-compat fallback** and is migrated
 > into the canonical location by `install` on the next run.
 
 All three are YAML. Schemas:
 
-- Developer (project-local): [`agent-settings.md`](../../templates/agent-settings.md).
-- Team: [`agent-project-settings.example.yml`](../../templates/agents/agent-project-settings.example.yml).
+- Developer (project-local): [`agent-settings.md`](../../../src/agent-src/templates/agent-settings.md).
+- Team: [`agent-project-settings.example.yml`](../../../src/agent-src/templates/agents/agent-project-settings.example.yml).
 - User-global: six exact dotted paths — whitelist in
   [`scripts/_lib/agent_settings.ts`](../../../src/scripts/_lib/agent_settings.ts).
 
@@ -42,7 +42,7 @@ Lowest priority → highest priority:
 1. Package defaults                                   (shipped by event4u/agent-config)
 2. ~/.event4u/agent-config/agent-settings.yml         (user-global · whitelist-filtered · legacy ~/.config/agent-config/ read as fallback)
 3. .agent-project-settings.yml                        (team file, committed)
-4. agents/settings/.agent-settings.yml                (developer file, gitignored; legacy repo-root .agent-settings.yml read as fallback — ADR-038)
+4. agents/settings/.agent-settings.yml                (developer file, gitignored; legacy repo-root .agent-settings.yml read as fallback — ADR-038) <!-- ref-ignore -->
 ```
 
 Keys from higher layers win unless a lower layer marks them
@@ -160,7 +160,7 @@ pattern (e.g. `*.yml` in a nested folder) would otherwise match.
 Module-aware skills and commands (`module-management`, `/module
 explore`, `/module create`, roadmap-writing) consult the `modules:`
 block on the **team** layer
-([`agent-project-settings.example.yml`](../../templates/agents/agent-project-settings.example.yml))
+([`agent-project-settings.example.yml`](../../../src/agent-src/templates/agents/agent-project-settings.example.yml))
 to find module roots, namespace conventions, and per-module
 `agents/` folders. Lives next to `project.stack` because it
 describes the same thing — repo layout.
@@ -253,14 +253,14 @@ after that.
 The contract is **additive merge with user-line preservation** —
 the user's file is the ground truth, the template only contributes
 keys the user is missing. Round-trip parser and merger live in
-[`scripts/sync_yaml_rt.ts`](../../src/scripts/sync_yaml_rt.ts); the
+[`scripts/sync_yaml_rt.ts`](../../../src/scripts/sync_yaml_rt.ts); the
 supported YAML subset (block-mappings, scalars, lists, comments,
 CRLF/LF) is documented in its module docstring. The stdlib-only
 choice (vs. `ruamel.yaml`) and its revisit triggers are recorded in
 [`docs/contracts/adr-settings-sync-engine.md`](../../contracts/adr-settings-sync-engine.md).
 
 For each section in the template
-([`agent-settings.md`](../../templates/agent-settings.md)):
+([`agent-settings.md`](../../../src/agent-src/templates/agent-settings.md)):
 
 - For each key under the section:
   - **Key exists in user's file** → keep the user's line **verbatim**
@@ -313,5 +313,5 @@ the next explicit settings edit.
 
 ## See also
 
-- [`agent-settings.md`](../../templates/agent-settings.md) — dev-layer schema
-- [`agent-project-settings.example.yml`](../../templates/agents/agent-project-settings.example.yml) — team-layer template
+- [`agent-settings.md`](../../../src/agent-src/templates/agent-settings.md) — dev-layer schema
+- [`agent-project-settings.example.yml`](../../../src/agent-src/templates/agents/agent-project-settings.example.yml) — team-layer template

package/docs/guidelines/agent-infra/memory-access.md

@@ -145,5 +145,5 @@ Other types remain accessible on demand via
 
 - [`engineering-memory-data-format.md`](engineering-memory-data-format.md)
   — the on-disk schema
-- [`../../rules/context-hygiene.md`](../../rules/context-hygiene.md)
+- [`../../rules/context-hygiene.md`](../../../src/rules/context-hygiene.md)
   — token budget that `max_entries_per_task` protects

package/docs/guidelines/agent-infra/mental-models.md

@@ -6,11 +6,11 @@ lens at a time. Adopted under the **Reference-Guideline Sunset Policy**
 (see frontmatter `upstream` / `refresh_trigger` keys) 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.
-- [`refine-prompt`](../../../.agent-src.uncondensed/skills/refine-prompt/SKILL.md)
+- [`refine-prompt`](../../../src/skills/refine-prompt/SKILL.md)
   — multi-lens prompt refinement.
-- [`judge-bug-hunter`](../../../.agent-src.uncondensed/skills/judge-bug-hunter/SKILL.md)
+- [`judge-bug-hunter`](../../../src/skills/judge-bug-hunter/SKILL.md)
   — diff review through more than the bug-hunter lens.
 
 > **Core principle:** "To a man with only a hammer, every problem looks