@event4u/agent-config 16.3.0 → 16.5.0

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

@@ -17,7 +17,6 @@ collision_ok:
   "src/skills/": "skill prose must not name derivation sources"
   "src/rules/": "rule prose must not name derivation sources"
   "agents/roadmaps/": "harvest/comparison roadmaps stay anonymized"
-# obligation: line 46
 obligation_frequency: "per-edit"
 ---
 

package/dist/agent-src/rules/source-discovery-gate.md

@@ -20,7 +20,6 @@ packs: [engineering-base]
 collision_ok:
   "endpoint": "an unconfirmed endpoint shape needs evidence before code"
   "schema": "a DB schema is the canonical structure to verify from a real source"
-# obligation: line 44
 obligation_frequency: "per-edit"
 ---
 

package/dist/agent-src/rules/source-of-truth.md

@@ -16,7 +16,6 @@ enforced_by:
   - "validator:src/scripts/check_condensation.ts"
 collision_ok:
   ".augment/": "the projection is read-only — edits belong in src/"
-# obligation: line 44
 obligation_frequency: "per-edit"
 ---
 

package/dist/agent-src/rules/spreadsheet-source-quality.md

@@ -14,7 +14,6 @@ workspaces:
   - finance
 packs:
   - finance-basic
-# obligation: line 49
 obligation_frequency: "per-edit"
 ---
 
@@ -60,5 +59,5 @@ Entering, updating, or charting **financial figures** in a spreadsheet / model.
 ## See also
 
 - [`spreadsheet-authoring`](../skills/spreadsheet-authoring/SKILL.md) — the spreadsheet surface floor this rule's sourcing discipline plugs into.
-- [`surface-agent-contracts`](../docs/contracts/surface-agent-contracts.md) — the spreadsheet surface's invariants + truth source.
+- `docs/contracts/surface-agent-contracts.md` — the spreadsheet surface's invariants + truth source.
 - [`finance-safety-floor`](finance-safety-floor.md) — the finance-pack advisory floor (not-investment-advice, sensitivity) this complements.

package/dist/agent-src/rules/strategy-safety-floor.md

@@ -36,7 +36,6 @@ trust:
   human_review_required: true
 collision_ok:
   "category": "'category' is positioning vocabulary (category design) in the strategy pack"
-# obligation: line 55
 obligation_frequency: "per-task"
 ---
 <!-- agent-config:human-review-banner -->

package/dist/agent-src/rules/symfony-routing.md

@@ -16,7 +16,6 @@ trust:
 install:
   default: false
   removable: true
-# obligation: line 23
 obligation_frequency: "none"
 ---
 
@@ -24,5 +23,5 @@ obligation_frequency: "none"
 
 **Iron Law.** Symfony-flavoured PHP → `symfony-workflow`. Discriminator: entry point and router, not the dependency list — `symfony/*` with no skeleton marker is the third verdict.
 
-Body migrated to `skill:symfony-workflow`. Disambiguates the laravel ↔ symfony-workflow cluster head per [`adr-architectural-consensus-mechanism`](../docs/contracts/adr-architectural-consensus-mechanism.md).
+Body migrated to `skill:symfony-workflow`. Disambiguates the laravel ↔ symfony-workflow cluster head per `docs/contracts/adr-architectural-consensus-mechanism.md`.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).

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

@@ -22,7 +22,6 @@ collision_ok:
   "implement": "analyze-first floor on any implementation"
   "debug": "targeted inspection over brute force while debugging"
   "fix": "no blind trial-and-error on fixes — max 2 retries"
-# obligation: line 50
 obligation_frequency: "per-edit"
 ---
 

package/dist/agent-src/rules/token-budget-discipline.md

@@ -8,7 +8,6 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
-# obligation: line 43
 obligation_frequency: "per-edit"
 ---
 
@@ -32,15 +31,10 @@ TO THE FULL FRUGALITY CANON (telegraph-speak, thin-projector).
 | `standard` | — | Balanced condensation | Not trimmed if priority ≥ 60 | 500–2000 tokens |
 | `rich` | Must be declared + justified | **Exempt** | **Never trimmed** | 2000–3500 tokens |
 
-Read `tokens.rich_skills` from `.agent-settings.yml` (default `on`) — the project
-layer of a cascade that starts user-global, so `agent-config settings:get
-tokens.rich_skills` is the read that answers it, file included — to determine
-whether rich skills may load in full. If `off`, treat them as `standard`. If
-`ask`, the question's shape is
-[`settings-ask-protocol`](settings-ask-protocol.md)'s, not this rule's; what only
-this rule knows is the number to put in it — the estimated token delta, ≈ skill
-file size in chars / 4. The answer is cached for the session and never persisted
-(`tokens.rich_skills` is class C).
+Rich skills always load in full — there is no setting to read. The
+`tokens.rich_skills` key that once allowed `off` / `ask` was retired on 2026-10-09
+with its default (`on`) as the fixed behavior; the skill's own
+`token_budget_class: rich` declaration plus the CI ceiling below is what decides.
 
 ## Requirements for `token_budget_class: rich`
 
@@ -57,15 +51,15 @@ A skill claiming `rich` MUST satisfy ALL three:
    carry a `load_context` pointer instead.
 
 3. **≤ 15 % of the suite's skills may claim `rich`** — the CI linter counts
-   rich-tagged skills and hard-fails if the ratio is exceeded. With 299 skills
-   the cap is ~44. Do not claim `rich` for convenience; claim it only for
+   rich-tagged skills and hard-fails if the ratio is exceeded. With 300 skills
+   the cap is ~45. Do not claim `rich` for convenience; claim it only for
    irreducible-complexity skills.
 
 ## Telegraph-speak amendment
 
-The telegraph-speak rule is **dormant by default** — absent
-`telegraph.speak` it does not project at all, so there is nothing to exempt
-from. Where a consumer has enabled it, it **exempts** skills marked
+The telegraph-speak rule is **dormant** — it does not project at all (a
+package-level decision in `compile_time_toggles.ts`), so there is nothing to
+exempt from. If it ever ships again, it **exempts** skills marked
 `token_budget_class: rich`. When such a skill is active:
 
 - Do not apply telegraph-speak condensation to its guidance prose
@@ -75,8 +69,7 @@ from. Where a consumer has enabled it, it **exempts** skills marked
 
 This exemption is limited to the skill's guidance content; reply prose from the
 *agent* (not from the skill body) remains subject to telegraph-speak wherever
-that rule ships at all (`telegraph.speak`), within the carve-outs the rule
-itself names.
+that rule ships at all, within the carve-outs the rule itself names.
 
 ## Value-over-budget escalation
 
@@ -104,17 +97,6 @@ canon: a near-miss where a net-positive frontend/design change was
 almost dropped purely on token-budget grounds is the canonical failure
 this escalation exists to prevent.
 
-## Candidate rich skills (justified, not exhaustive)
-
-These skills are approved `rich` by this roadmap's council:
-
-| Skill | Justification summary |
-|---|---|
-| `design-intelligence` | 11 corpus CSVs + 16 design-language prose specs + a 10-category checklist; grounded selection needs the full reference to avoid random corpus subsets |
-| `typography-system` | Modular-scale math + 6 worked example type systems; condensing to "use 1.25 ratio" produces agents that invent arbitrary px values |
-| `accessibility-auditor` | WCAG criteria are non-negotiable detail; every criterion has a testable condition + failure mode; compression loses the test procedures |
-| `design-system-capture` (Phase 6) | Writes + maintains DESIGN.md + PRODUCT.md; needs full templates + worked examples to generate useful artifacts |
-
 ## Rich artifacts lead with a non-negotiable band
 
 ```
@@ -138,34 +120,18 @@ be shorter — that is the ceiling, gated below, and the two controls are
 independent: an artifact can sit comfortably under the ceiling and still bury
 its obligation on line 300.
 
-## The size band is measured, and only its ceiling is gated
-
-The `rich` band is **2,000–3,500 tokens** (ADR-217, `docs/decisions/ADR-217-rich-class-band-measured-and-enforced.md`).
-It was 2,000–5,000 and enforced by nothing until that record: measured with the
-exact BPE tokenizer, the largest rich artifact in the tree is 3,331 tokens, so
-the old ceiling described no artifact that existed. An unused permission costs
-nothing until someone uses it.
-
-`lint_token_budget_discipline.ts` gates the **ceiling** and publishes every rich
-artifact's size on the green path. It does **not** gate the floor, and that is a
-finding rather than an omission: running the check once surfaced a 1,931-token
-skill legitimately holding the class, because `rich` buys exemption from
-condensation — a claim about what compression would *lose*, not about file size.
-The published study supplies a degradation threshold, which is a ceiling.
-Nothing measures a minimum.
+## The size band
 
-Measurement is exact where `js-tiktoken` resolves and the character proxy where
-it does not; the gate says which, and a proxy reading within its own error
-margin of the ceiling is reported **unresolved** rather than classified.
+`rich` is **2,000–3,500 tokens** (ADR-217); only the ceiling is gated, by
+`lint_token_budget_discipline.ts`. Why no floor, and the approved candidate
+list: `guideline:agent-infra/size-and-scope` § Rich-class size band.
 
 ## Governed by
 
-- `tokens.rich_skills` setting in `.agent-settings.yml` (consumer override)
 - `lint_token_budget_discipline.ts` (cap + justification + ceiling CI check)
 - the telegraph-speak rule, where enabled (amended to except rich-tagged skills)
 
 ## See also
 
 - `token_budget_class` key in `src/scripts/schemas/skill.schema.json`
-- `tokens.rich_skills` in `src/config/agent-settings.template.yml`
 - the telegraph-speak rule, where enabled — the frugality canon this rule amends

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

@@ -11,7 +11,6 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
-# obligation: line 21
 obligation_frequency: "per-edit"
 ---
 

package/dist/agent-src/rules/token-optimizer-maintenance.md

@@ -19,7 +19,6 @@ workspaces: [agent-config-maintainer]
 packs: [meta]
 enforced_by:
   - "validator:src/scripts/check_token_optimizer_freshness.ts"
-# obligation: line 29
 obligation_frequency: "per-commit"
 ---
 

package/dist/agent-src/rules/tool-safety.md

@@ -11,7 +11,6 @@ workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 enforced_by:
   - "validator:src/scripts/lint_agent_security.ts"
-# obligation: line 19
 obligation_frequency: "per-edit"
 evidence:
   source_type: external-standard

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

@@ -45,7 +45,6 @@ collision_ok:
   "*.tsx": "one component file, two obligations: inventory before the write, review after it"
   "*.jsx": "one component file, two obligations: inventory before the write, review after it"
   "*.blade.php": "one template file, two obligations: inventory before the write, review after it"
-# obligation: line 39
 obligation_frequency: "per-edit"
 ---
 
@@ -155,7 +154,7 @@ Warn-only, capped at two per session, default-OFF, and bound only in the three
 (**clarified 2026-08-17**: "where a slot exists" read as a host property, and it
 is a manifest one; three further hosts alias a native pre-tool event without a
 binding, and only claude honours a deny at all — the four states are tabulated
-in [`hook-architecture-v1 § Which hosts carry pre_tool_use`](../docs/contracts/hook-architecture-v1.md)).
+in `docs/contracts/hook-architecture-v1.md` § Which hosts carry pre_tool_use).
 None of that changes the verdict here: a reminder that can be ignored is not a
 gate, so `enforced_by:` stays `none`. Run `agent-config hooks:status` for the
 host you are on rather than trusting this sentence.

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

@@ -20,7 +20,6 @@ workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:
   - "instruction-only: no deterministic gate inspects fetched content for injected instructions; injection_scan_hook is warn-only and default-OFF"
-# obligation: line 38
 obligation_frequency: "per-event"
 evidence:
   source_type: external-standard

package/dist/agent-src/rules/upstream-proposal.md

@@ -10,7 +10,6 @@ routes_to:
   - "skill:upstream-contribute"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
-# obligation: line 17
 obligation_frequency: "per-task"
 ---
 

package/dist/agent-src/rules/user-interaction.md

@@ -13,7 +13,6 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
-# obligation: line 40
 obligation_frequency: "per-turn"
 ---
 

package/dist/agent-src/rules/user-interrupt-priority.md

@@ -19,7 +19,6 @@ load_context:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
-# obligation: line 38
 obligation_frequency: "per-turn"
 ---
 

package/dist/agent-src/scripts/gate_budget.ts

@@ -56,9 +56,16 @@ export function gateBudgetLedgerPath(workspaceRoot: string): string {
 }
 
 /** The two caps decided by option (a). Both are USD. */
+/**
+ * The two standing caps, each independently settable.
+ *
+ * Both figures are **US dollars**. Either may be `null`, meaning that cap was
+ * not set and therefore bounds nothing; `readGateBudgetCaps` returns `null`
+ * for the whole object only when NEITHER was set.
+ */
 export interface GateBudgetCaps {
-    maxCostPerRunUsd: number;
-    maxCostPerRolling7dUsd: number;
+    maxCostPerRunUsd: number | null;
+    maxCostPerRolling7dUsd: number | null;
 }
 
 /**
@@ -105,18 +112,26 @@ function _dig(settings: unknown, keys: readonly string[]): unknown {
 /**
  * Read the caps out of an already-merged settings dict.
  *
- * Returns `null` when either cap is absent or non-numeric — deliberately NOT a
- * fallback to the template numbers. An install whose settings do not carry the
- * caps has not authorised a standing budget, and inventing one from the
- * template default would authorise spend nobody configured. The caller renders
- * the consent line instead.
+ * Each cap is returned on its own. Returns `null` only when NEITHER is set,
+ * which means no ceiling on money was configured — not that the run is
+ * unauthorised. Still deliberately NOT a fallback to the template numbers:
+ * inventing a cap from a template default would bound a run by a figure
+ * nobody chose.
+ *
+ * Until 2026-10-06 this returned `null` unless BOTH caps were numeric, with
+ * two consequences. A person who set one cap and left the other alone was
+ * bounded by NEITHER — the stricter-looking rule produced the laxer result.
+ * And absent caps were read by the caller as a refusal, so the gate would not
+ * run at all without them. ADR-279 supersedes that second reading: absence of
+ * a bound is not a bound, and `--confirm` remains the authorisation the caps
+ * only ever sized.
  */
 export function readGateBudgetCaps(settings: unknown): GateBudgetCaps | null {
     const perRun = _num(_dig(settings, ['roadmap', 'gate_budget', 'max_cost_per_run_usd']));
     const rolling = _num(
         _dig(settings, ['roadmap', 'gate_budget', 'max_cost_per_rolling_7d_usd']),
     );
-    if (perRun === null || rolling === null) {
+    if (perRun === null && rolling === null) {
         return null;
     }
     return { maxCostPerRunUsd: perRun, maxCostPerRolling7dUsd: rolling };
@@ -216,13 +231,15 @@ export function rollingSpendUsd(records: readonly GateBudgetReceipt[], now: Date
 }
 
 export type GateBudgetRefusal =
-    | 'no_caps'
+    // 'no_caps' was removed on 2026-10-06 with ADR-279: the absence of a cap
+    // is no longer a refusal, so no path can produce it and leaving it in the
+    // union would advertise a verdict nothing returns.
     | 'no_estimate'
     | 'over_per_run'
     | 'over_rolling_7d';
 
 export type GateBudgetVerdict =
-    | { ok: true; estimateUsd: number; rollingUsd: number }
+    | { ok: true; estimateUsd: number | null; rollingUsd: number }
     | { ok: false; reason: GateBudgetRefusal; detail: string };
 
 /**
@@ -230,6 +247,12 @@ export type GateBudgetVerdict =
  *
  * Every refusal path renders rather than runs — the blocker's own prescription
  * for a missing ledger, generalised to every way the budget can say no.
+ *
+ * What is NOT a refusal, per ADR-279: the absence of a cap. With no cap
+ * configured there is no ceiling on money to compare anything against, so the
+ * verdict is `ok` and the run proceeds on the authorisation `--confirm`
+ * already carries. A cap that WAS set still bounds exactly as its contract
+ * describes, and each bounds alone.
  */
 export function evaluateGateBudget(opts: {
     caps: GateBudgetCaps | null;
@@ -238,16 +261,17 @@ export function evaluateGateBudget(opts: {
     now: Date;
 }): GateBudgetVerdict {
     const { caps, records, estimateUsd, now } = opts;
-    if (caps === null) {
-        return {
-            ok: false,
-            reason: 'no_caps',
-            detail:
-                'no standing class-1 budget is configured ' +
-                '(`roadmap.gate_budget.max_cost_per_run_usd` and ' +
-                '`roadmap.gate_budget.max_cost_per_rolling_7d_usd`)',
-        };
+    const perRunCap = caps === null ? null : caps.maxCostPerRunUsd;
+    const rollingCap = caps === null ? null : caps.maxCostPerRolling7dUsd;
+    // No ceiling on money was set anywhere, so nothing here can say no.
+    // `rollingUsd` is still computed and reported — recording spend never
+    // depended on bounding it.
+    if (perRunCap === null && rollingCap === null) {
+        return { ok: true, estimateUsd, rollingUsd: rollingSpendUsd(records, now) };
     }
+    // A missing estimate refuses only because a cap exists that nothing can be
+    // compared against. With no cap there is no comparison to fail, which is
+    // why this sits BELOW the no-cap branch rather than above it.
     if (estimateUsd === null) {
         return {
             ok: false,
@@ -257,17 +281,17 @@ export function evaluateGateBudget(opts: {
                 'can be compared against it',
         };
     }
-    if (estimateUsd > caps.maxCostPerRunUsd) {
+    if (perRunCap !== null && estimateUsd > perRunCap) {
         return {
             ok: false,
             reason: 'over_per_run',
             detail:
                 `the estimate ($${estimateUsd.toFixed(2)}) exceeds the per-run cap ` +
-                `($${caps.maxCostPerRunUsd.toFixed(2)})`,
+                `($${perRunCap.toFixed(2)})`,
         };
     }
     const spent = rollingSpendUsd(records, now);
-    if (spent + estimateUsd > caps.maxCostPerRolling7dUsd) {
+    if (rollingCap !== null && spent + estimateUsd > rollingCap) {
         return {
             ok: false,
             reason: 'over_rolling_7d',
@@ -275,7 +299,7 @@ export function evaluateGateBudget(opts: {
                 `$${spent.toFixed(2)} is already receipted in the last ` +
                 `${String(ROLLING_WINDOW_DAYS)} days and this run would add ` +
                 `$${estimateUsd.toFixed(2)}, over the rolling cap ` +
-                `($${caps.maxCostPerRolling7dUsd.toFixed(2)})`,
+                `($${rollingCap.toFixed(2)})`,
         };
     }
     return { ok: true, estimateUsd, rollingUsd: spent };

package/dist/agent-src/scripts/gate_execute.ts

@@ -297,7 +297,12 @@ function execute(
     // generalised to every way the budget can say no. The `--confirm`
     // requirement below is untouched: the caps bound the size of an authorised
     // spend, they never supply the authorisation.
-    let budgeted: { estimateUsd: number } | null = null;
+    // `estimateUsd` is null only on the one path that reaches here without a
+    // USD figure: a class-1 entry that states no estimate AND an install with
+    // no cap set, so there was no cap for the missing estimate to fail
+    // against. A receipt needs a number, and inventing 0 would understate the
+    // ledger, so that path runs and reports that nothing was receipted.
+    let budgeted: { estimateUsd: number | null } | null = null;
     if (cls === '1') {
         const verdict = evaluateGateBudget({
             caps: readGateBudgetCaps(load_agent_settings({ cwd: repoRoot })),
@@ -388,7 +393,7 @@ function execute(
             code: 1,
         };
     }
-    if (budgeted !== null) {
+    if (budgeted !== null && budgeted.estimateUsd !== null) {
         // Written BEFORE the file rewrite: an unreceipted spend is invisible to
         // the rolling cap, and the cap failing open is the one way this
         // mechanism could become a blank cheque. `actual_usd` is null because
@@ -421,8 +426,11 @@ function execute(
             `and the status flipped to resolved ${when}.\n` +
             (budgeted === null
                 ? ''
-                : `Receipt appended to ${LEDGER_REL} ` +
-                  `($${budgeted.estimateUsd.toFixed(2)} estimated).\n`) +
+                : budgeted.estimateUsd === null
+                  ? `No receipt appended to ${LEDGER_REL}: the entry states no USD ` +
+                    'estimate and no cap is configured, so there is no figure to record.\n'
+                  : `Receipt appended to ${LEDGER_REL} ` +
+                    `($${budgeted.estimateUsd.toFixed(2)} estimated).\n`) +
             // The dashboard is derived from the file this just rewrote, so it
             // is now stale. Saying so is the same follow-up `renderResumed`
             // already prints for its own file-move suggestion.

package/dist/agent-src/skills/accessibility-auditor/data/aria-patterns.csv

@@ -11,3 +11,5 @@ Skip link & landmarks,skip link landmark main nav banner region,landmarks + skip
 Drag and drop / reorder,drag drop reorder sortable kanban move,keyboard-equivalent commands,Every drag operation has a keyboard path (move-up/move-down buttons or grab mode with arrows + announcements); aria-live announces position changes,"WCAG 2.1.1, 2.5.7",Pointer-only reordering,https://www.w3.org/WAI/ARIA/apg/patterns/listbox/
 Loading / busy state,loading spinner skeleton busy progress,aria-busy + progressbar/status,Region marked aria-busy during load OR role=progressbar with valuenow; announce completion via status region; skeletons are aria-hidden,WCAG 4.1.3,Spinner gif with no text alternative; focus lost on content swap,https://www.w3.org/WAI/ARIA/apg/patterns/meter/
 Icon-only button,icon button close edit delete aria-label svg,accessible name on control,aria-label (or visually-hidden text) on the button; svg aria-hidden=true focusable=false; hit area ≥44px,"WCAG 4.1.2, 2.5.8",title attribute as the only name; emoji as icon,https://www.w3.org/WAI/ARIA/apg/patterns/button/
+Meaningful standalone graphic,svg graphic chart diagram illustration logo standalone meaningful accessible name title desc,role=img + referenced title/desc,"role=img on the svg; a direct child title (plus optional desc) referenced by aria-labelledby using ids namespaced per instance; never aria-label together with title; delivered through img, the host alt is the accessible name and the inline title is unreachable","WCAG 1.1.1, 4.1.2","Generic id=""title"" reused by two inline graphics, so both announce the first one's name; title present without role=img; aria-label and title on the same element",https://www.w3.org/WAI/tutorials/images/complex/
+Decorative graphic,decorative ornament flourish background presentational aria-hidden empty alt svg,aria-hidden + empty host alt,"aria-hidden=true and focusable=false on the svg; delivered through img, an empty alt (never a missing alt, which lets the file name become the name); the graphic carries no title",WCAG 1.1.1,Alt text describing an ornament; aria-hidden on a graphic carrying the only copy of its information,https://www.w3.org/WAI/tutorials/images/decorative/

package/dist/agent-src/skills/accessibility-auditor/data/manifest.json

@@ -27,8 +27,8 @@
   "owner": "package-maintainer",
   "refresh_cadence": "quarterly",
   "upstream": {
-    "repo": "derived: W3C ARIA Authoring Practices Guide + WCAG 2.2",
-    "sha": "WCAG 2.2 W3C-REC-2024-12-12; APG continuously-published, menu-button canonical slug",
-    "last_checked": "2026-10-01"
+    "repo": "derived: W3C ARIA Authoring Practices Guide + WCAG 2.2 + W3C WAI Images Tutorial",
+    "sha": "WCAG 2.2 W3C-REC-2024-12-12; APG continuously-published, menu-button canonical slug; the two graphic rows re-derived 2026-10-11 from the WAI Images Tutorial (complex, decorative) against WCAG 1.1.1 / 4.1.2, and both retrieval queries re-run after the append — 'meaningful standalone svg chart graphic accessible name' moved off the icon-button row, 'icon only close button' kept it",
+    "last_checked": "2026-10-11"
   }
 }

package/dist/agent-src/skills/ai-council/SKILL.md

@@ -67,7 +67,10 @@ things follow, and the first is the one under pressure:
 2. **Do not bounce to the user just because the council failed.** An
    unreachable council does not upgrade a decidable question into a
    user-required one. Decide it, label it own analysis, state the reason the
-   council was unavailable, and name what would change the answer.
+   council was unavailable, and name what would change the answer. Not for a
+   modification review (a change to the gated surface or one the learning
+   lanes originate, ADR-281): there an unavailable council stops the run for
+   the user per `docs/contracts/ratification-artifact.md`.
 3. **Escalate only if it is genuinely undecidable without them** — the two
    options are close AND the cost of being wrong is high AND nothing in the tree
    separates them. Then say the council was attempted and why it failed, so the
@@ -311,9 +314,9 @@ attributed to the host.
   identity — that primes the reviewer and collapses diversity.
 - Do NOT silently truncate a too-large bundle — surface the size and
   ask for narrower scope.
-- Do NOT spend against an unbounded budget without asking — a billable
-  member with neither `max_total_usd` nor `daily_limit_usd` set has no
-  ceiling, and autonomy is not a ceiling.
+- Do NOT ask for permission because no cap is set. ADR-279: a spend bound
+  applies only where one was set, and the absence of one is not a reason
+  to ask. Show the estimate as information and run.
 - Do NOT reuse SDK clients across invocations — re-load keys via
   `load_*_key()` each call.
 

package/dist/agent-src/skills/ai-council/references/cost-and-redaction.md

@@ -47,6 +47,10 @@ table)` and render a per-member table. Heuristic: `len(text) / 4` for
 input, member's `max_tokens` ceiling for output (actual spend is
 usually lower).
 
+This block is **information shown before the run**, not a prompt. Per
+ADR-279 the absence of a cap is not a reason to ask, so there are no
+numbered options here and nothing waits for an answer.
+
 > External council call — billable
 >
 > Mode: roadmap · Target: `agents/roadmaps/<name>.md` (~3 KB after redaction)
@@ -57,21 +61,27 @@ usually lower).
 > | openai / gpt-4o                 |      ~750 / 1024     |  $0.0121 |
 > | **total**                       |                      | **$0.0297** |
 >
-> Budget: 50k in / 20k out tokens · USD ceiling: $0.50
->
-> 1. Run the consultation
-> 2. Cancel
+> Budget: no cap set — token and USD ceilings are `0`.
+
+The `Budget:` line states whatever the user configured. With nothing
+configured it says so plainly, as above; with a cap set it names the
+figure and its unit (`50k in / 20k out tokens · USD ceiling: $0.50`).
+A cap that exists is what `on_overrun` fires against, below.
 
-### Stale price-table gate
+### Stale price table — stated, not asked
 
-If `pricing.is_stale(table)` returns true, ask before proceeding:
+If `pricing.is_stale(table)` returns true, say so in the same block and
+proceed. ADR-237 § 3 already requires that a cost which cannot be
+determined exactly is estimated conservatively and asked nothing about,
+and a stale table is exactly that case:
 
-> Price table is stale (last_updated: YYYY-MM-DD)
-> 1. Refresh now (`./scripts-run src/scripts/update_prices`)
-> 2. Continue with the stale table
-> 3. Cancel
+> Note: price table last updated YYYY-MM-DD and may be stale, so the
+> figures above are an estimate. Refresh with
+> `./scripts-run src/scripts/update_prices`.
 
-Do not silently auto-refresh — the user keeps control.
+Do not silently auto-refresh — the user keeps control of when prices
+change. Stating the staleness is what keeps that control without
+turning it into a question.
 
 ### Mid-flow overrun callback (`on_overrun`)
 

package/dist/agent-src/skills/ai-council/references/procedure.md

@@ -45,14 +45,20 @@ have not migrated yet).
      authorization the user already gave. Render the estimate and fan out.
      `on_overrun` still fires per member on breach (below) — that is where
      the user regains the decision.
-   - **Billable members with no ceiling at all** (`max_total_usd: 0` AND
-     `daily_limit_usd: 0`) → unbounded paid spend, so surface the estimate
-     and require an explicit `1`. Nothing bounds the call, so the user must.
+   - **Billable members with no cap set** (`max_total_usd: 0` AND
+     `daily_limit_usd: 0`, which is the shipped default) → render the
+     estimate as information and fan out. **No ask.** Per ADR-279 a spend
+     bound applies only where one was set, and the absence of one is not
+     a reason to ask.
 
-   Autonomy settings do not *create* a bound and do not lift the last case.
-   Consumers who want the old per-run gate back set a small
+   All three cases now behave the same way: the estimate is information,
+   never a prompt. What differs is only whether a cap exists for
+   `on_overrun` to fire against.
+
+   Consumers who want a per-run gate set a small
    `cost_budget.max_total_usd`: every call then breaches and `on_overrun`
-   asks, per member.
+   asks, per member. That is a bound they chose, which is the only kind
+   this procedure recognises.
 4. **Fan out.** Dispatch the bundle to each enabled council member via
    `scripts/ai_council/orchestrator.ts`. Each member receives the
    neutrality preamble from `prompts.ts` plus the artefact — nothing

package/dist/agent-src/skills/analysis-autonomous-mode/SKILL.md

@@ -109,7 +109,7 @@ Constraint: **attack the biggest unknown first** (not breadth-first). Repeat unt
 | New evidence appears | Re-evaluate all conclusions |
 | Stuck in one skill | Broaden — switch to `universal-project-analysis` |
 | Clear pattern recognized | Narrow — go deep with the right specialist |
-| 3 failed attempts | Stop — summarize state, ask user for direction |
+| 3 failed attempts | Change approach — `autonomous-execution`'s mandatory strategy shift, never a stop |
 
 ## Learning from past analyses
 

package/dist/agent-src/skills/bug-analyzer/SKILL.md

@@ -53,7 +53,7 @@ Pattern matching:
 - `fix/DEV-1234/description` → extract `DEV-1234`
 - `fix/PROJ-567-some-bug` → extract `PROJ-567`
 - `hotfix/DEV-999` → extract `DEV-999`
-- Regex: `[A-Z]+-[0-9]+`
+- Read it with `agent-config git:convention ticket` — [`commit-subject`](../git-workflow/references/commit-subject.md) § Reading the ticket
 
 If found, auto-fetch the ticket and confirm with the user.
 

package/dist/agent-src/skills/canvas-design/SKILL.md

@@ -1,7 +1,7 @@
 ---
 model_tier: inherit
 name: canvas-design
-description: "Creating static visual art — posters, marketing visuals, brand assets, PDF/PNG design pieces — on 'design a poster' or 'mach uns ein Visual'. Grounded by design-intelligence."
+description: "Static visual art — posters, marketing visuals, brand assets, PDF/PNG pieces — on 'design a poster' or 'mach uns ein Visual'."
 domain: product
 workspaces:
   - small-business
@@ -73,7 +73,9 @@ Document it in `philosophy.md` under `## Subtle reference`.
 
 Produce `agents/design-assets/{slug}/{slug}.{pdf|png}`:
 
-1. Pick the execution tool (Pillow, matplotlib, SVG, or framework-native)
+1. Pick the execution tool (Pillow, matplotlib, SVG, or framework-native). When
+   it is SVG, author it under [`svg-authoring`](../svg-authoring/SKILL.md) —
+   the canvas is still an asset and gets the same static check and witness
 2. **Font selection** — pick a font that earns the philosophy. Inspect a working dir (e.g. `agents/design-assets/{slug}/fonts/` — create if missing) and place the chosen file there before render. System defaults (Arial, Helvetica, DejaVu, the matplotlib default sans) are the AI-template tell; reach for them only as deliberate fallback, never as the unexamined default
 3. Limited palette — 2–5 colors, intentional and cohesive
 4. Geometric or organic forms per philosophy