@event4u/agent-config 14.22.0 → 15.0.0

package/dist/agent-src/rules/code-comment-discipline.md

@@ -63,12 +63,12 @@ Test before writing any comment: *would deleting it leave a future reader confus
 - The user explicitly asks for documented code / teaching examples ("erkläre im Code", "annotate this for juniors") — that turn's ask wins.
 - License headers or file-level pragmas a toolchain requires.
 
-Body migrated to [`guideline:code-clarity § Comment discipline`](../docs/guidelines/code-clarity.md#comment-discipline--state-a-constraint-not-a-narration) (per P4 of `road-to-kernel-and-router.md`) — banned-classes table, machine-relevant precision carve-out, `code_style.docblocks` public-API carve-out, per-language keep/drop tables, worked examples, scope boundary, fixtures pointer.
+Body migrated to [`guideline:code-clarity § Comment discipline`](../guidelines/code-clarity.md#comment-discipline--state-a-constraint-not-a-narration) (per P4 of `road-to-kernel-and-router.md`) — banned-classes table, machine-relevant precision carve-out, `code_style.docblocks` public-API carve-out, per-language keep/drop tables, worked examples, scope boundary, fixtures pointer.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also
 
-- [`code-clarity.md § Comment discipline`](../docs/guidelines/code-clarity.md#comment-discipline--state-a-constraint-not-a-narration) — canonical long-form with the migrated body.
+- [`code-clarity.md § Comment discipline`](../guidelines/code-clarity.md#comment-discipline--state-a-constraint-not-a-narration) — canonical long-form with the migrated body.
 - [`minimal-safe-diff`](minimal-safe-diff.md) — diff-shape twin; no comment additions or removals on untouched code.
 - [`output-discipline`](output-discipline.md) — adjacent but distinct: bans placeholder prose (`// TODO: implement`); this rule bans redundant prose.
 - `docs/guidelines/php/php-coding-patterns.md` § PHPDoc — PHP-specific operationalization.

package/dist/agent-src/rules/code-provenance.md

@@ -162,7 +162,7 @@ is why the discipline is the control on both layers.
   **The carve-out is authorship, not delivery:** a vendored component or a
   licensed template that merely *arrives inside* a handover stays under this
   rule in full. Boundary stated from the other side in
-  [`design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md)
+  [`design-fidelity-mechanics`](../guidelines/design-fidelity-mechanics.md)
   § Adopt the code.
   **It exempts the code clauses only.** A claim *about* the artifact's origin —
   that a pattern in it came from somewhere nameable — is a knowledge-layer

package/dist/agent-src/rules/content-quoting-floor.md

@@ -83,7 +83,7 @@ does not substitute for engaging with the source.
   how much of that data may be reproduced verbatim once it IS being
   used as source material.
 - [`code-provenance`](code-provenance.md) +
-  [`design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md)
+  [`design-fidelity-mechanics`](../guidelines/design-fidelity-mechanics.md)
   § Adopt the code — this rule's user-owned-text carve-out extended to
   **markup**: a design artifact the user hands over is their own material, so
   adapting its code is not a borrow. Third-party code arriving inside that

package/dist/agent-src/rules/context-hygiene.md

@@ -92,7 +92,7 @@ tool calls and a waiter is indistinguishable from any other call at that layer.
 
 Why the loop test misses it in both clauses, the n=1 measurement behind the
 clause, and the enforcement argument: [`context-hygiene-mechanics § Waiting is one
-waiter`](../docs/guidelines/agent-infra/context-hygiene-mechanics.md).
+waiter`](../guidelines/agent-infra/context-hygiene-mechanics.md).
 
 ## Read-Loop Detection — the 15 / 25 rule
 
@@ -110,12 +110,12 @@ EVERY TURN MUST EDIT, RUN, OR ASK.
 
 ### Declared read protocol — the cap goes UP, never off
 
-A mandated analysis/audit/review protocol is exactly the case that legitimately needs *more* reads, not fewer — an 8-turn evidence sweep is the protocol working, not a loop. Capping a declared protocol tighter than an undeclared one is backwards. So:
+A mandated analysis/audit/review protocol — or a port of a provided design artifact, where reading the handover whole IS the work — is exactly the case that legitimately needs *more* reads, not fewer — an 8-turn evidence sweep is the protocol working, not a loop. Capping a declared protocol tighter than an undeclared one is backwards. So:
 
 - **Undeclared reading keeps 3-warn / 5-abort.** Unchanged.
 - **A declared protocol raises the abort to 8 read-only turns** — and never suspends it. "Non-bypassable" narrows to **no *silent* bypass**: a declared protocol is not silent.
 
-> **The 8 is a guess, a LOWER BOUND, and revisitable** — derivation, the n=1 run behind it, and the two-branch `revisit-if`: [`context-hygiene-mechanics § The declared-protocol cap`](../docs/guidelines/agent-infra/context-hygiene-mechanics.md).
+> **The 8 is a guess, a LOWER BOUND, and revisitable** — derivation, the n=1 run behind it, and the two-branch `revisit-if`: [`context-hygiene-mechanics § The declared-protocol cap`](../guidelines/agent-infra/context-hygiene-mechanics.md).
 
 A declaration is only valid when it states, before the reading starts, all three of:
 
@@ -125,10 +125,10 @@ A declaration is only valid when it states, before the reading starts, all three
 
 Free-text intent is not a declaration — the three fields exist so that "declared protocol: I need to read things" cannot buy the higher cap. Exceeding the declared count by more than 2 is itself the violation: stop, surface what the extra reads were for, and ask.
 
-Body migrated to [`guideline:agent-infra/context-hygiene-mechanics`](../docs/guidelines/agent-infra/context-hygiene-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — the freshness-suggestion template, the read-loop self-check + abort block, the state-dump format + `/agent-handoff` pointer, the Augment ignored-skills recovery flow, and the Copilot no-hook fallback (manual `context_hygiene_hook` refresh).
+Body migrated to [`guideline:agent-infra/context-hygiene-mechanics`](../guidelines/agent-infra/context-hygiene-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — the freshness-suggestion template, the read-loop self-check + abort block, the state-dump format + `/agent-handoff` pointer, the Augment ignored-skills recovery flow, and the Copilot no-hook fallback (manual `context_hygiene_hook` refresh).
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also
 
-- [`guideline:agent-infra/context-hygiene-mechanics`](../docs/guidelines/agent-infra/context-hygiene-mechanics.md) — templates + per-host procedures.
+- [`guideline:agent-infra/context-hygiene-mechanics`](../guidelines/agent-infra/context-hygiene-mechanics.md) — templates + per-host procedures.
 - [`systematic-debugging § Debug micro-loop`](../skills/systematic-debugging/SKILL.md) — the read-loop debug procedure.

package/dist/agent-src/rules/cross-source-consistency.md

@@ -88,7 +88,7 @@ trivial edits, or when the user has already resolved the discrepancy this turn.
 
 The taxonomy, the scan procedure, the confidence-tiered noise control, worked
 examples, and the precedence table live in
-[`cross-source-consistency-mechanics`](../docs/guidelines/agent-infra/cross-source-consistency-mechanics.md).
+[`cross-source-consistency-mechanics`](../guidelines/agent-infra/cross-source-consistency-mechanics.md).
 
 ## See also
 

package/dist/agent-src/rules/design-fidelity.md

@@ -25,6 +25,7 @@ triggers:
   - phrase: "1:1 nach"
   - phrase: "claude.site/artifacts"
   - file_pattern: "*design.html"
+  - file_pattern: "*.dc.html"
   - path_prefix: ".claude/design-system/"
 applies_to_user_types:
   - "creator"
@@ -75,12 +76,12 @@ both of which name a screenshot as a legitimate spec — and it would forbid the
 image-only handover class the rule exists to govern. What it forbids is
 narrower: reaching for pixels **while the code is sitting there**.
 
-The five new lines route to
-[`design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md)
-§ Data-basis ladder (the first three) and § Adopt the code (the last two) —
-including the scope line that keeps the adopt-the-code duty from colliding with
-[`code-provenance`](code-provenance.md). Read that scope line before acting on
-either rule; the boundary is stated from both sides.
+**Artifact versus brand — arbitrated here, not behind a pointer.** A brand
+token wins on a **value** (colour, type, spacing), and the distance from the
+artifact's own value is reported, never silently absorbed. **Structure is the
+artifact's** — layout, controls, component set, order, breakpoints — never
+adjusted to suit a token; a conflict is surfaced, never merged. The
+adopt-the-code duty stops where [`code-provenance`](code-provenance.md) starts.
 
 ## What counts as the spec
 
@@ -105,7 +106,7 @@ mentions a wireframe it replaces routes **strictly** — a reference to a previo
 not a declaration about this one. **When the artefact does not declare its maturity,
 it is treated as finished**: the 1:1 floor is stricter, and guessing *low fidelity*
 would authorise the redesign this rule prevents. Maturity→spec table + the pinned near-miss:
-[`design-fidelity-mechanics § Artefact maturity`](../docs/guidelines/design-fidelity-mechanics.md).
+[`design-fidelity-mechanics § Artefact maturity`](../guidelines/design-fidelity-mechanics.md).
 
 ## Strictness — set by `design.fidelity_mode`
 
@@ -120,6 +121,12 @@ design.fidelity_mode` reports the value and the file it came from.
 | `structural` | Structure is locked — fonts, control types, component set, layout, no omissions still require confirmation. Where the spec is genuinely **silent** (a state it does not show: hover / empty / error), the agent may fill the gap in the spec's style and MUST state the assumption. |
 | `hard-floor` | Any deviation from the provided design is a Hard-Floor action (per [`non-destructive-by-default`](non-destructive-by-default.md)): never autonomous; no autonomy setting, roadmap, or standing instruction lifts it. |
 
+**Inside a configured tolerance, `strict` reports a reconciliation rather than
+demanding a confirmation** — conditional on `design.approximation`, which ships
+disabled with both tolerances `null`, so no default install changes. Structure,
+and anything outside tolerance, is unchanged; `hard-floor` disables it outright:
+[`design-reconciliation § Tolerance`](../guidelines/design-reconciliation.md).
+
 ## When it fires
 
 A finished design artifact is provided or referenced AND the agent is building,
@@ -136,10 +143,13 @@ porting, or modifying UI to match it.
 Matching is plain lower-cased substring containment on the prompt, plus fnmatch
 over the open files. Three handover classes must reach this rule: an English
 phrasing, a German one, and a prompt carrying **no** keyword at all because the
-artifact is simply attached. The last is covered by `file_pattern: *design.html`
-— the conventional handover filename, not `*.html`, which would fire on every
-HTML edit in every project and be strictly worse than the gap it closes. A
-handover under some other filename needs one word in the prompt.
+artifact is simply attached. The last is covered by two file patterns:
+`*design.html`, the conventional handover filename, and `*.dc.html`, the Claude
+Design canvas artboard — which `*design.html` cannot match, because it compiles
+to `^(?:.*design\.html)$` and `ToDo.dc.html` does not end in `design.html`.
+Neither is `*.html`, which would fire on every HTML edit in every project and be
+strictly worse than the gap it closes; `near-plain-html-open-file` pins that
+form silent. A handover under some other filename needs one word in the prompt.
 
 Two further handover shapes carry the artifact without any of the above:
 
@@ -153,43 +163,23 @@ Two further handover shapes carry the artifact without any of the above:
   vendor-scoped directory, never a bare `design-system/`, which is a normal
   source folder in a large fraction of frontend repos.
 - **A third-party builder's share link — UNCOVERED, deliberately.** A page built
-  in Lovable / v0 / bolt and handed over as a link is a finished spec, and this
-  rule does not route it. The obvious trigger was tried on this branch and
-  **withdrawn**: matching is plain substring containment, so `https://v0.dev/`
-  also fires on `https://v0.dev/docs`, a pricing page, or a changelog link — it
-  would treat every mention of the tool's own site as a spec handover. That is
-  the `claude.ai` failure the capability-URL entry above exists to avoid, and by
-  this rule's own standard it is worse than the gap it closes. The alternatives
-  are a bare-host keyword (broader still) or guessing each vendor's share-path
-  segment, and a trigger built on a guessed path is not evidence.
-  **What closes it:** a verified share-path segment per vendor, or a
-  handover-word co-occurrence the matcher cannot express today. Until then the
-  class needs one word in the prompt, like any other unlisted filename.
-  `near-bare-host-mention` in the matrix pins the bare-host direction silent so
-  a future attempt cannot reintroduce the broad form unnoticed.
-
-The trigger set is deliberately phrase-heavy on the German side and on
-`artifact`: a bare `artifact` keyword fires on "the CI build artifact is 40 MB".
-`ROUTING_MATRIX` in
-[`design_fidelity_routing.test.ts`](../../tests/scripts/design_fidelity_routing.test.ts)
-pins both halves — every class that must route, and the near-misses that must
-stay silent (fixture `daf-port-trigger-de`). Extending the set without adding a
-near-miss row there is how an over-broad trigger lands: each of the two shipped
-trigger classes above carries its own near-miss row
-(`near-claude-ai-chat-link`, `near-generic-design-system-dir`), and the
-withdrawn builder-URL class left `near-bare-host-mention` behind so the broad
-form stays pinned silent.
+  in Lovable / v0 / bolt and handed over as a link is a finished spec and this
+  rule does not route it; the trigger was tried and withdrawn as over-broad.
+  Until then the class needs one word in the prompt. Why, what closes it, and
+  the row that pins the broad form silent:
+  [`design-fidelity-routing`](../guidelines/design-fidelity-routing.md).
+
+Every class here carries its own near-miss row in `ROUTING_MATRIX`
+([`design_fidelity_routing.test.ts`](../../tests/scripts/design_fidelity_routing.test.ts));
+extending the set without one is how an over-broad trigger lands. Which row, and
+why: [`design-fidelity-routing`](../guidelines/design-fidelity-routing.md).
 
 **The near-miss must test the direction the new trigger opens, not a direction
-that was already closed.** The withdrawn class is the worked example: its first
-near-miss row tested a protocol-less mention, which was silent *before* the
-change and therefore could not have caught the over-broadness the change
-introduced. The row that would have caught it is
-`near-builder-host-non-handover-url` — a documentation URL on the same host —
-and it exists only because a review asked for it after the trigger had already
-shipped. Write that row first next time; it is the cheap half.
-
-Body migrated to [`guideline:design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — URL / live-page handover (extraction into the `design-system.json` contract before the first UI write, the retrieval order, the lock boundary), surgical visual edits (targeted-edit vs redesign-trigger discipline, stable anchors), asset & imagery discipline (owned-asset path, third-party delivery is self-hosted by default, real-imagery-as-proof, iconography floor, no unrequested filler), deviation-surfacing shape, failure-mode catalog, `daf-*` fixtures.
+that was already closed** — apply this before writing a trigger, not after. The
+worked example and the review that produced the rule:
+[`design-fidelity-routing`](../guidelines/design-fidelity-routing.md).
+
+Body migrated to [`guideline:design-fidelity-mechanics`](../guidelines/design-fidelity-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — URL / live-page handover (extraction into the `design-system.json` contract before the first UI write, the retrieval order, the lock boundary), surgical visual edits (targeted-edit vs redesign-trigger discipline, stable anchors), asset & imagery discipline (owned-asset path, third-party delivery is self-hosted by default, real-imagery-as-proof, iconography floor, no unrequested filler), deviation-surfacing shape, failure-mode catalog, `daf-*` fixtures.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/direct-answers.md

@@ -30,7 +30,7 @@ THE MORE LOAD-BEARING THE CLAIM, THE HARDER YOU VERIFY.
 WHEN VERIFICATION IS NOT WORTH THE COST → ASK.
 ```
 
-Severity tiers, per-tier verification actions, "just guess" override, **no duration estimates**, and **never cite the rule** when declining: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md).
+Severity tiers, per-tier verification actions, "just guess" override, **no duration estimates**, and **never cite the rule** when declining: [`asking-and-brevity-examples`](../guidelines/agent-infra/asking-and-brevity-examples.md).
 
 **Live-state facts — never from memory.** Git/PR merge/branch/sync/existence state is High-severity and decays silently (branch already merged, PR already closed, `main` already ahead). NEVER assert "merged / not merged / pending / still open / already in `main` / out of scope" — or any branch/sync/existence claim — from memory, a roadmap note, an earlier turn, or a recalled memory. Run the live check FIRST (`git log --first-parent origin/main`, `git branch -r --contains <ref>`, `gh pr view <n> --json state,mergedAt,baseRefName`); a state question is self-answering (per [`git-workflow`](../skills/git-workflow/SKILL.md)). Same for any external system that changes behind you (CI run, deploy, remote queue).
 
@@ -57,6 +57,6 @@ Never overrides `user-interaction` (numbered options) or command steps. Reply-cl
 
 ## Failure modes & examples
 
-Triggers + corrections: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md). Wrong/right/why: [`direct-answers-demos`](../docs/guidelines/agent-infra/direct-answers-demos.md). Baseline: [`tests/golden/outcomes/direct_answers.json`](../../tests/golden/outcomes/direct_answers.json).
+Triggers + corrections: [`asking-and-brevity-examples`](../guidelines/agent-infra/asking-and-brevity-examples.md). Wrong/right/why: [`direct-answers-demos`](../guidelines/agent-infra/direct-answers-demos.md). Baseline: [`tests/golden/outcomes/direct_answers.json`](../../tests/golden/outcomes/direct_answers.json).
 
 Cross-rule index: [`frugality-charter`](../contexts/contracts/frugality-charter.md).

package/dist/agent-src/rules/domain-adoption-policy.md

@@ -48,7 +48,7 @@ replace the gate evidence. Any gate not citeable → **defer** + a watch-only
 note under `agents/settings/contexts/domain-watch/<domain>.md`; never silently
 shrink scope to dodge a gate.
 
-Body migrated to [`guideline:agent-infra/domain-adoption-gates`](../docs/guidelines/agent-infra/domain-adoption-gates.md) (per P4 of `road-to-kernel-and-router.md`) — per-gate evidence bars (demand signal, named owner + cadence, CI-vs-reference-only), the sunset policy, the failure-mode catalog, the gates-fail procedure, and the allowed-without-gates list.
+Body migrated to [`guideline:agent-infra/domain-adoption-gates`](../guidelines/agent-infra/domain-adoption-gates.md) (per P4 of `road-to-kernel-and-router.md`) — per-gate evidence bars (demand signal, named owner + cadence, CI-vs-reference-only), the sunset policy, the failure-mode catalog, the gates-fail procedure, and the allowed-without-gates list.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/evaluator-independence.md

@@ -139,7 +139,7 @@ review ran as if it were verified.
 Why each branch behaves that way, the phrase-list and turn-boundary limits, the
 four host states, the two corrections this section has taken, and the
 11-of-19 measurement behind item 3:
-[`evaluator-independence-mechanics`](../docs/guidelines/agent-infra/evaluator-independence-mechanics.md).
+[`evaluator-independence-mechanics`](../guidelines/agent-infra/evaluator-independence-mechanics.md).
 
 ## See also
 

package/dist/agent-src/rules/framework-neutrality-in-generic-skills.md

@@ -83,7 +83,7 @@ Framework names in a generic artifact appear only as **multi-stack peers**
 mandated procedure. `scripts/lint_framework_leakage.ts` is the deterministic
 CI backstop (exit 1 on a non-allowlisted hit in a generic artifact).
 
-Body migrated to [`guideline:agent-infra/framework-neutrality-patterns`](../docs/guidelines/agent-infra/framework-neutrality-patterns.md) (per P4 of `road-to-kernel-and-router.md`) — the 10-row forbidden-pattern table with fixes, the cross-stack documentation allowance + auto-detect heuristic, the carve-out pointer shape, and the linter exit-code contract.
+Body migrated to [`guideline:agent-infra/framework-neutrality-patterns`](../guidelines/agent-infra/framework-neutrality-patterns.md) (per P4 of `road-to-kernel-and-router.md`) — the 10-row forbidden-pattern table with fixes, the cross-stack documentation allowance + auto-detect heuristic, the carve-out pointer shape, and the linter exit-code contract.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/icon-consistency.md

@@ -44,12 +44,16 @@ Any of the trigger keywords appear in a UI-building context: new component, new
 
 ## When NOT to fire
 
+- **An icon traceable to a provided design artifact.** A faithful port
+  reproduces the handover's own icons; one traceable to neither the icon set nor
+  a named artifact still fires. A new rung below the brand token, never a
+  re-ordering: [`design-reconciliation § Icons on a provided artifact`](../guidelines/design-reconciliation.md).
 - The project's brand guide explicitly defines multiple icon sets for distinct contexts (e.g., filled icons for navigation, outlined for inline text).
 - The task is documentation or a non-UI surface (scripts, CLI output, markdown).
 - The user explicitly scopes to "just explore options" without committing to a UI change.
 
 ## See also
 
-- [`design-canon.md`](../docs/guidelines/design-canon.md) § Icon systems — when a named design system is in play, prefer its icon set over a fresh Iconify pick.
+- [`design-canon.md`](../guidelines/design-canon.md) § Icon systems — when a named design system is in play, prefer its icon set over a fresh Iconify pick.
 - [`iconography`](../skills/iconography/SKILL.md) — full icon-system selection, audit, and migration workflow.
 - [`ui-audit-gate`](ui-audit-gate.md) — broader UI consistency gate; runs before any new component lands.

package/dist/agent-src/rules/improve-before-implement.md

@@ -56,7 +56,7 @@ Run, in order: **1. Is the request clear?** · **2. Does it fit the existing arc
 
 Verification stays concrete — a `curl` probe against the endpoint, a Playwright spec, an `xdebug` step-through, or the project's test runner with a targeted filter — never a from-memory assertion (full section in the guideline below).
 
-Body migrated to [`guideline:agent-infra/agent-interaction-and-decision-quality` § 8](../docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md#8-improve-before-implement--pre-implementation-validation) (per P4 of `road-to-kernel-and-router.md`) — the three checks' detail, how-to-challenge example, scope limits, verify-with-concrete-tools, RDP intent-inference.
+Body migrated to [`guideline:agent-infra/agent-interaction-and-decision-quality` § 8](../guidelines/agent-infra/agent-interaction-and-decision-quality.md#8-improve-before-implement--pre-implementation-validation) (per P4 of `road-to-kernel-and-router.md`) — the three checks' detail, how-to-challenge example, scope limits, verify-with-concrete-tools, RDP intent-inference.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## The golden rule

package/dist/agent-src/rules/language-and-tone.md

@@ -40,7 +40,7 @@ Stays source-language: code blocks, command output, file contents, quoted tool o
 1. **Detect** — language of last chat message. Mixed → dominant; tie → German.
 2. **Scan** — every user-visible token per catalog.
 3. **Rewrite** — one wrong-language token → rewrite whole reply.
-4. **Confirm** — first sentence in target language; recommendation label matches; no wrong-language filler opener. Blocklist: [`language-and-tone-examples`](../docs/guidelines/agent-infra/language-and-tone-examples.md).
+4. **Confirm** — first sentence in target language; recommendation label matches; no wrong-language filler opener. Blocklist: [`language-and-tone-examples`](../guidelines/agent-infra/language-and-tone-examples.md).
 
 ## Spelled out
 
@@ -53,7 +53,7 @@ Stays source-language: code blocks, command output, file contents, quoted tool o
 
 Acknowledge **once**, correct language ("Entschuldigung" / "Sorry"), switch in the same reply. No wrong-language re-explain; no "from now on" promise.
 
-Examples + CLI spacing rules + wrong-vs-correct: [`language-and-tone-examples`](../docs/guidelines/agent-infra/language-and-tone-examples.md).
+Examples + CLI spacing rules + wrong-vs-correct: [`language-and-tone-examples`](../guidelines/agent-infra/language-and-tone-examples.md).
 
 ## `.md` files — ALWAYS English
 
@@ -61,4 +61,4 @@ All `.md` text under `src/`, `docs/`, `.augment/`, `dist/agent-src/`, `.agent-sr
 
 Genuinely-required German → one of the two sanctioned escapes (labeled `DE: … · EN: …` anchor, or per-line `<!-- md-language-check: ignore -->` marker) — canonical mechanics in the guideline below.
 
-Generated-output rule, escape mechanics, pre-save detection heuristic: [`language-and-tone-examples`](../docs/guidelines/agent-infra/language-and-tone-examples.md).
+Generated-output rule, escape mechanics, pre-save detection heuristic: [`language-and-tone-examples`](../guidelines/agent-infra/language-and-tone-examples.md).

package/dist/agent-src/rules/minimal-safe-diff.md

@@ -78,7 +78,7 @@ Your diff cleans up exactly the mess it made — nothing more:
   own-orphan (delete); otherwise → note. (`downstream-changes` runs the same
   sweep for renames — this is that sweep applied to the new diff.)
 
-Body migrated to [`guideline:agent-infra/minimal-safe-diff-mechanics`](../docs/guidelines/agent-infra/minimal-safe-diff-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — larger-change guidance, auto-formatter hunk handling, anti-over-engineering criteria (premature abstraction, speculative features, rewrite trigger, no tombstones + the council's rejected trust-internal-code clause), break-glass exception, and the full bounded-remediation carve-out prose (five conditions summarized: same path/module, ≤ ~10 lines, no API change, no dependency/migration, verification in the same commit — everything outside is note + ask per `active-remediation`; a live cross-user/tenant exposure is the sole interrupt).
+Body migrated to [`guideline:agent-infra/minimal-safe-diff-mechanics`](../guidelines/agent-infra/minimal-safe-diff-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — larger-change guidance, auto-formatter hunk handling, anti-over-engineering criteria (premature abstraction, speculative features, rewrite trigger, no tombstones + the council's rejected trust-internal-code clause), break-glass exception, and the full bounded-remediation carve-out prose (five conditions summarized: same path/module, ≤ ~10 lines, no API change, no dependency/migration, verification in the same commit — everything outside is note + ask per `active-remediation`; a live cross-user/tenant exposure is the sole interrupt).
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/notes-first-reasoning.md

@@ -24,11 +24,8 @@ obligation_frequency: "per-turn"
 # Notes-First Reasoning
 
 Part of the Reasoning Discipline Protocol. Engage per
-[`rdp-gate`](../contexts/execution/rdp-gate.md) (settings + task-signal + host
-self-assessment) — skip on trivial tasks; apply lightly on a strong-reasoning
-host. The notes file is grounded in the documented cross-run lessons memory
-(consolidated via [`memory-consolidation`](../skills/memory-consolidation/SKILL.md));
-the in-task sections below are a local derivation for within-task scope.
+[`rdp-gate`](../contexts/execution/rdp-gate.md) — skip on trivial tasks, apply
+lightly on a strong-reasoning host.
 
 ## The Iron Law
 
@@ -38,36 +35,50 @@ NOTES FILE — NEVER ECHOED INTO THE RESPONSE.
 THE RESPONSE CARRIES CONCLUSIONS + EVIDENCE ONLY.
 ```
 
-Reasoning dumped into the user-facing answer is both noise and a
-`reasoning_extraction` refusal risk (see `rdp-gate`). Keep it in the notes file.
-This is not "show your work in the reply" — it is the opposite.
+This is not "show your work in the reply" — it is the opposite. Why, and what
+grounds the notes file:
+[`notes-horizon-mechanics`](../guidelines/agent-infra/notes-horizon-mechanics.md).
 
 ## Notes file structure (the file, not the response)
 
-Use the sections that apply; the structure carries the enumeration, so there is
-no "write N hypotheses" instruction — record what the work actually surfaced.
+Use the sections that apply — record what the work actually surfaced.
 
 - `## In-Task Hypothesis Log` — competing explanations under consideration.
-- `## Killed beliefs` — each discarded hypothesis + the evidence that killed it.
-- `## Predictions` — prediction · confidence · result · lesson (the calibration
-  loop: hypothesis → prediction → reality → calibration).
-- `## Decisions` — decision · alternatives · reason · revisit-if. Tactical,
-  in-task decisions stay here; **escalate to
-  [`decision-record`](../skills/decision-record/SKILL.md)/ADR** when the decision
-  is cross-task or architectural (litmus: would a dev on a different component
-  next month need this context?).
+- `## Killed beliefs` — each discarded hypothesis + the `killed-if` that killed
+  it.
+- `## Predictions` — **chosen form** · prediction · confidence · result · lesson.
+- `## Decisions` — decision · alternatives · reason · revisit-if ·
+  **next-commitment**. Tactical decisions stay here; **escalate to
+  [`decision-record`](../skills/decision-record/SKILL.md)/ADR** when cross-task
+  or architectural.
 - `## Uncertainty` — per-dimension score (e.g. architecture/implementation/
   requirements: high/medium/low); feeds the adaptive-effort decision.
 
+### The horizon — where `next-commitment` ends
+
+```
+A CHOICE AUTHORISES WORK UP TO THE NEXT EVIDENCE-PRODUCING BOUNDARY.
+NAME THE BOUNDARY FROM THE LIST. NEVER "THE WORK THE EVIDENCE SUPPORTS" —
+THAT IS A JUDGEMENT, AND A JUDGEMENT IS NOT A HORIZON.
+```
+
+### Reopening — once, on contradiction, never on a schedule
+
+```
+AN OBSERVATION THAT CONTRADICTS THE PREDICTION REOPENS THE CHOICE BEFORE THE
+NEXT STEP — FROM THE CANDIDATE LIST THAT ALREADY EXISTS, NEVER A FRESH
+ENUMERATION. ONE REOPEN PER CANDIDATE. THE SECOND CONTRADICTION HANDS OVER TO
+THE RETRY-BUDGET LADDER RATHER THAN REOPENING AGAIN.
+```
+
 ## What stays out of notes
 
-User-attribute facts, transient TODOs, and durable cross-run lessons — those go
-to the memory system (`memory-consolidation`), not the in-task notes.
+User-attribute facts, transient TODOs, and durable cross-run lessons go to the
+memory system (`memory-consolidation`), not the in-task notes.
 
 ## See also
 
-- [`rdp-gate`](../contexts/execution/rdp-gate.md) — the table-free engagement gate.
-- [`memory-consolidation`](../skills/memory-consolidation/SKILL.md) — promotes
-  durable lessons across runs.
-- [`verify-before-complete`](verify-before-complete.md) — the evidence the
-  response carries comes from real tool results.
+[`notes-horizon-mechanics`](../guidelines/agent-infra/notes-horizon-mechanics.md)
+— every mechanic this rule points at. Also
+[`rdp-gate`](../contexts/execution/rdp-gate.md) and
+[`verify-before-complete`](verify-before-complete.md).

package/dist/agent-src/rules/recurring-criticism.md

@@ -75,7 +75,7 @@ resolution naming none of them is an unresolved recurrence.
 **Look up the earlier disposition before re-deriving anything, and name the store
 you checked** — addresses, the mechanism-is-the-defect classification, the
 hardening floor and the failure modes are in
-[`recurring-criticism-mechanics`](../docs/guidelines/agent-infra/recurring-criticism-mechanics.md).
+[`recurring-criticism-mechanics`](../guidelines/agent-infra/recurring-criticism-mechanics.md).
 One line does not migrate, because acting on it wrong is silent: rejections live in
 analysis prose by design, so "I found nothing" means *prose was grepped*, never
 *nothing was decided*.

package/dist/agent-src/rules/roadmap-progress-sync.md

@@ -97,7 +97,7 @@ in the estate?**
   *whether the work happens*; only fix-now discharges it, and a carried item
   untouched at the next task boundary is raised again per
   [`active-remediation`](active-remediation.md). Provenance and the argument:
-  [`roadmap-deferred-resolution-provenance`](../docs/guidelines/agent-infra/roadmap-deferred-resolution-provenance.md).
+  [`roadmap-deferred-resolution-provenance`](../guidelines/agent-infra/roadmap-deferred-resolution-provenance.md).
 
 ### `deferred_policy` — a declared contract removes the round, never the route
 

package/dist/agent-src/rules/role-mode-adherence.md

@@ -17,7 +17,7 @@ obligation_frequency: "per-turn"
 
 Auto-activates when `.agent-settings.yml` sets `roles.active_role` to
 one of the six modes defined in
-[`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md):
+[`role-contracts`](../guidelines/agent-infra/role-contracts.md):
 `developer`, `reviewer`, `tester`, `po`, `incident`, `planner`.
 
 Read `roles.active_role` from `.agent-settings.yml` at session start — the project layer of a cascade that starts user-global, so use `agent-config settings:get roles.active_role`, which reports the value and the file it came from, rather than opening one file. Empty / missing → rule is inert; do NOT guess a mode.
@@ -54,7 +54,7 @@ Infer the mode (Phase-3 router does that). Touch `.agent-settings.yml`
 
 ## See also
 
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md)
+- [`role-contracts`](../guidelines/agent-infra/role-contracts.md)
 - [`/mode`](../commands/mode.md)
 - [`ask-when-uncertain`](ask-when-uncertain.md)
 - [`scope-control`](scope-control.md)

package/dist/agent-src/rules/security-sensitive-stop.md

@@ -79,7 +79,7 @@ Run the matching analysis skill first:
 | Wide refactor of security-sensitive code | `blast-radius-analyzer` |
 
 **Before running the analysis, consult memory for prior incidents** on
-this surface. Via [`memory-access`](../docs/guidelines/agent-infra/memory-access.md):
+this surface. Via [`memory-access`](../guidelines/agent-infra/memory-access.md):
 
 ```bash
 agent-config memory:lookup \

package/dist/agent-src/rules/size-enforcement.md

@@ -36,7 +36,7 @@ real, sourced entries** per skill.
   - Rules and system instructions should stay well below 200 lines
   - Smaller (≈60 lines) is strongly preferred
 
-→ Size limits and details: `../docs/guidelines/agent-infra/size-and-scope.md`
+→ Size limits and details: `../guidelines/agent-infra/size-and-scope.md`
 
 → Frontmatter contract: schemas live in `scripts/schemas/` and are enforced by
 `./scripts-run src/scripts/validate_frontmatter`.

package/dist/agent-src/rules/source-confidentiality.md

@@ -98,14 +98,14 @@ path trigger to match, and a path-scoped rule is not re-injected after
 measurement, the AI-council record of 2026-08-20, the three rejected
 alternatives and the +3,512-token cost this shared note carries for four rules
 live in
-[`source-confidentiality-mechanics`](../docs/guidelines/agent-infra/source-confidentiality-mechanics.md)
+[`source-confidentiality-mechanics`](../guidelines/agent-infra/source-confidentiality-mechanics.md)
 § Why these four rules are unconditional — moved there 2026-08-29 because a
 rationale paid on every subagent spawn is the most expensive place to keep an
 argument nobody re-reads.
 
 ## See also
 
-- [`source-confidentiality-mechanics`](../docs/guidelines/agent-infra/source-confidentiality-mechanics.md) — the claim/residual honesty clause, the two-class split by path, and the gate's shape checks and tiering.
+- [`source-confidentiality-mechanics`](../guidelines/agent-infra/source-confidentiality-mechanics.md) — the claim/residual honesty clause, the two-class split by path, and the gate's shape checks and tiering.
 - [`source-of-truth`](source-of-truth.md) — edit `src/`, never the projections.
 - [`augment-edit-discipline`](augment-edit-discipline.md) — portability + cross-ref sync.
 - `src/scripts/_lib/link_crypto.ts` — encrypted link storage.

package/dist/agent-src/rules/think-before-action.md

@@ -45,7 +45,7 @@ NO BLIND TRIAL-AND-ERROR. MAX 2 RETRIES PER APPROACH.
 - Unclear requirements → precise clarification question, not hidden assumptions.
 - Refactors must preserve behavior, validation, examples, and anti-failure guidance unless explicitly changed.
 - Do NOT modify code you do not fully understand — read it, trace the flow, then change it.
-- Multiple valid frameworks/patterns coexist (Tailwind + Flux, multiple form libs, competing state stores) → do NOT pick one silently — ask. See [`no blind implementation`](../docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md#2-no-blind-implementation).
+- Multiple valid frameworks/patterns coexist (Tailwind + Flux, multiple form libs, competing state stores) → do NOT pick one silently — ask. See [`no blind implementation`](../guidelines/agent-infra/agent-interaction-and-decision-quality.md#2-no-blind-implementation).
 
 ## The intent line, before a behaviour-changing edit
 

package/dist/agent-src/rules/token-efficiency.md

@@ -101,11 +101,13 @@ content — size, then a structural grep for the offsets that matter, then a
 ranged read of those offsets. Below it, just read it: a probe you did not need
 costs a call and teaches nothing.
 
-The number is a **stated default, not a measured optimum** — said plainly rather
-than implying a derivation it does not have. *Revisit-if:* a run records a
-probe-then-slice that cost more than the full read would have, or the host's
-ranged-read primitive changes its own default. Either falsifies the number, not
-the obligation.
+The number is a **stated default, not a measured optimum**; its `revisit-if`
+lives in the mechanics file below.
+
+**Carve-out — a provided design artifact.** A handover is routinely thousands of
+lines and reading it whole IS the task, not a probe target. Before the threshold
+above applies, declare the read per
+[`context-hygiene`](context-hygiene.md) § Declared read protocol.
 
 Additive: the repetition discriminator above is untouched, an enumerated
 multi-file sweep stays ONE operation, and re-probing a file whose shape you

package/dist/agent-src/rules/ui-audit-gate.md

@@ -123,8 +123,9 @@ limits, because naming a script is not the same as closing the gap:
    `post_tool_use`.
 
 Run [`existing-ui-audit`](../skills/existing-ui-audit/SKILL.md) before adding a
-component because reuse beats duplication. What changed is that a check can now
-catch you — on a host that binds the slot, with the setting on, and not on the
+component because reuse beats duplication — **except against a provided
+artifact, where it is conditional on the candidate conforming** (that skill
+§ 6b). What changed is that a check can now catch you — on a host that binds the slot, with the setting on, and not on the
 very first file of a new surface.
 
 **A runtime carrier now exists, and it does not change the verdict.** The

package/dist/agent-src/rules/untrusted-input-defense.md

@@ -79,14 +79,14 @@ inflation, so none is counted.
 hook that cannot refuse does not enforce. This section used to say no such
 backstop existed and that a future one would change the field — the first half
 is now false, the second always was. Detail:
-[`untrusted-input-spotlighting § The content-scanning hook`](../docs/guidelines/agent-infra/untrusted-input-spotlighting.md).
+[`untrusted-input-spotlighting § The content-scanning hook`](../guidelines/agent-infra/untrusted-input-spotlighting.md).
 
-Body migrated to [`guideline:agent-infra/untrusted-input-spotlighting`](../docs/guidelines/agent-infra/untrusted-input-spotlighting.md) (per P4 of `road-to-kernel-and-router.md`) — runtime defense protocol (separate / spotlight / refuse role-takeover / no silent egress / untrusted agent-instruction files), hidden-instruction awareness (invisible Unicode + confusables), injection-signal taxonomy, least-agency → existing-gate OWASP mapping.
+Body migrated to [`guideline:agent-infra/untrusted-input-spotlighting`](../guidelines/agent-infra/untrusted-input-spotlighting.md) (per P4 of `road-to-kernel-and-router.md`) — runtime defense protocol (separate / spotlight / refuse role-takeover / no silent egress / untrusted agent-instruction files), hidden-instruction awareness (invisible Unicode + confusables), injection-signal taxonomy, least-agency → existing-gate OWASP mapping.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also
 
-- [`untrusted-input-spotlighting`](../docs/guidelines/agent-infra/untrusted-input-spotlighting.md) — spotlighting/datamarking + OWASP LLM01/LLM06 mapping + the migrated body.
+- [`untrusted-input-spotlighting`](../guidelines/agent-infra/untrusted-input-spotlighting.md) — spotlighting/datamarking + OWASP LLM01/LLM06 mapping + the migrated body.
 - [`delegation-policy`](delegation-policy.md) — delegation authority; the found-instructions quarantine is where a container-delegation's scope ends.
 - [`lethal-trifecta-guard`](lethal-trifecta-guard.md) — break one leg of the trifecta.
 - [`security-sensitive-stop`](security-sensitive-stop.md), [`threat-modeling`](../skills/threat-modeling/SKILL.md), [`security-audit`](../skills/security-audit/SKILL.md).