@event4u/agent-config 8.4.1 → 8.6.0

package/dist/agent-src/commands/sync.md

@@ -0,0 +1,58 @@
+---
+model_tier: medium
+name: sync
+disable-model-invocation: true
+pack: meta
+intent: "Sync dispatcher — agent settings or the managed .gitignore block"
+routes_to: [sync-agent-settings, sync-gitignore, sync-gitignore-fix]
+replaces: []
+tier: 2
+visibility: internal
+description: Sync orchestrator — routes to agent-settings (template sync) and gitignore (managed block sync, plus legacy-cleanup fix)
+cluster: sync
+type: orchestrator
+suggestion:
+  eligible: false
+  rationale: "Settings/file sync — must be deliberate."
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# /sync
+
+Top-level orchestrator for the `/sync` family — keeping consumer-side
+managed files in step with the package templates.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/sync agent-settings` | `commands/sync/agent-settings.md` | Sync `.agent-settings.yml` against the current template + profile — adds new keys, preserves user values, diff before write |
+| `/sync gitignore` | `commands/sync/gitignore.md` | Sync the managed `event4u/agent-config` block in the consumer's `.gitignore` — append-only, diff before write |
+| `/sync gitignore-fix` | `commands/sync/gitignore/fix.md` | Scrub legacy pre-`/agents/` patterns anywhere in the `.gitignore`, then re-sync the canonical entries |
+
+Sub-command names match the locked contract in
+[`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md).
+
+## Dispatch
+
+1. Parse the user's argument: `/sync <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the corresponding sub-command file and follow its
+   `## Instructions` (or `## Steps`) section verbatim.
+4. If the sub-command is unknown or missing, print the menu and ask — do not
+   guess:
+
+   > 1. agent-settings — sync `.agent-settings.yml` with the template
+   > 2. gitignore — sync the managed `.gitignore` block (append-only)
+   > 3. gitignore-fix — scrub legacy patterns + re-sync canonical entries
+
+## Rules
+
+- **Diff before write, always.** Every `/sync` sub-command shows the proposed
+  diff and waits for approval before touching the file.
+- **Do NOT chain sub-commands.** One `/sync <sub>` per turn.
+- If the user invokes `/sync` with no argument, **show the menu** — do not
+  guess which sub-command they meant.

package/dist/agent-src/commands/{e2e-heal.md → tests/e2e-heal.md}

@@ -1,9 +1,12 @@
 ---
 model_tier: medium
-name: e2e-heal
+name: tests-e2e-heal
 pack: engineering-base
 tier: 2
 visibility: internal
+replaces: [e2e-heal]
+sub: e2e-heal
+cluster: tests
 skills: [playwright-testing]
 description: Find, debug, and fix failing Playwright E2E tests
 suggestion:
@@ -30,7 +33,7 @@ packs:
 > 2. Fix a specific test file — which one?
 > 3. Fix tests that failed in CI — provide the CI run URL or error output
 
-- Read the Playwright guideline: `../docs/guidelines/e2e/playwright.md`
+- Read the Playwright guideline: `../../docs/guidelines/e2e/playwright.md`
 
 ### 2. Run failing tests
 

package/dist/agent-src/commands/{e2e-plan.md → tests/e2e-plan.md}

@@ -1,9 +1,12 @@
 ---
 model_tier: medium
-name: e2e-plan
+name: tests-e2e-plan
 pack: engineering-base
 tier: 2
 visibility: internal
+replaces: [e2e-plan]
+sub: e2e-plan
+cluster: tests
 skills: [playwright-testing]
 description: Explore the application and create a structured E2E test plan in Markdown
 suggestion:
@@ -30,7 +33,7 @@ packs:
 > 2. Which feature area? (e.g., "checkout flow", "user settings", or "all visible flows")
 > 3. Is there an existing seed/setup file? (e.g., `tests/e2e/fixtures/auth.ts`)
 
-- Read the Playwright guideline: `../docs/guidelines/e2e/playwright.md`
+- Read the Playwright guideline: `../../docs/guidelines/e2e/playwright.md`
 - Check for existing test plans in `specs/` or `tests/e2e/specs/`.
 
 ### 2. Explore the application

package/dist/agent-src/commands/tests.md

@@ -5,14 +5,14 @@ disable-model-invocation: true
 pack: engineering-base
 tier: 2
 visibility: internal
-description: Tests orchestrator — routes to create, execute
+description: Tests orchestrator — routes to create, execute, e2e-plan, e2e-heal
 cluster: tests
 type: orchestrator
 auto_detect: true
 suggestion:
   eligible: true
-  trigger_description: "write tests for these changes, run the test suite"
-  trigger_context: "user wants to author or run tests for the current branch"
+  trigger_description: "write tests for these changes, run the test suite, plan E2E coverage, fix failing playwright tests"
+  trigger_context: "user wants to author or run tests for the current branch, or plan/heal Playwright E2E coverage"
 workspaces:
   - agent-config-maintainer
 packs:
@@ -30,9 +30,11 @@ commands with a single entry point + sub-command dispatch.
 |---|---|---|
 | `/tests create` | `commands/tests/create.md` | Write meaningful tests for the changes in the current branch (stack-adaptive) |
 | `/tests execute` | `commands/tests/execute.md` | Run the project's test suite — stack-adaptive (pest / phpunit / vitest / jest / pytest / …) |
+| `/tests e2e-plan` | `commands/tests/e2e-plan.md` | Explore the application and create a structured E2E test plan in Markdown |
+| `/tests e2e-heal` | `commands/tests/e2e-heal.md` | Find, debug, and fix failing Playwright E2E tests |
 
 Sub-command names match the locked contract in
-[`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
+[`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md).
 Both sub-commands resolve the runner via the
 [`toolchain-resolver`](../contexts/execution/toolchain-resolver.md) — they
 adapt to the consumer's stack instead of assuming one.
@@ -48,7 +50,9 @@ the `auto_detect` kill-switch, rollback). Detection table:
 | Explicit sub given (`/tests create`) | that one | — (detection skipped) |
 | "write/author tests", changed source files lack matching tests | `tests/create` | MEDIUM |
 | "run/execute the suite", a test command/run is the intent | `tests/execute` | HIGH |
-| No clear create-vs-run signal | — | LOW → menu (interactive) / `ambiguous_routing` (CI) |
+| "plan E2E coverage", new feature/page without `tests/e2e/` coverage | `tests/e2e-plan` | HIGH |
+| Failing Playwright output in context, "fix the E2E tests" | `tests/e2e-heal` | HIGH |
+| No clear signal | — | LOW → menu (interactive) / `ambiguous_routing` (CI) |
 
 create-vs-run is the only disambiguation: prefer `execute` when the
 intent is to run an existing suite; `create` when authoring new tests.
@@ -66,6 +70,8 @@ Neither is destructive past the normal test-run side effects.
 
    > 1. create — author tests for current-branch changes
    > 2. execute — run the test suite in Docker
+   > 3. e2e-plan — explore the app and write a structured E2E test plan
+   > 4. e2e-heal — find, debug, and fix failing Playwright tests
 
 ## Rules
 

package/dist/agent-src/contexts/augment-infrastructure.md

@@ -104,13 +104,13 @@ Commands organized by workflow:
 | **Contexts** | `context-create`, `context-refactor` |
 | **Modules** | `module-create`, `module-explore` |
 | **Roadmaps** | `roadmap:create`, `roadmap:process-step`, `roadmap:process-phase`, `roadmap:process-full` |
-| **Quality** | `quality-fix`, `review-changes`, `prepare-for-review`, `update-form-request-messages`, `fix-seeder` |
+| **Quality** | `fix-quality`, `review-changes`, `prepare-for-review`, `update-form-request-messages`, `fix-seeder` |
 | **CI/PR** | `fix-ci`, `create-pr`, `create-pr-description`, `fix-pr-comments` |
 | **Testing** | `tests-create`, `tests-execute` |
-| **E2E** | `e2e-plan`, `e2e-heal` |
+| **E2E** | `tests-e2e-plan`, `tests-e2e-heal` |
 | **Agents** | `agents-prepare`, `agents-audit`, `agents-cleanup`, `copilot-agents-optimize`, `agent-handoff`, `agent-status`, `optimize-agents`, `optimize-augmentignore`, `optimize-skills`, `optimize-rtk-filters` |
 | **Overrides** | `override-create`, `override-manage` |
-| **Config** | `onboard`, `set-cost-profile`, `commit` |
+| **Config** | `onboard`, `cost-profile`, `commit` |
 | **Packages** | `package-test`, `package-reset` |
 | **Project** | `project-analyze`, `project-health`, `jira-ticket` |
 

package/dist/agent-src/contexts/execution/auto-dispatch-classification.md

@@ -55,6 +55,36 @@ dwarfs the work). Below the floor → in-session.
 | `parallelizable: files\|independent` / independent slices | `do-in-parallel` |
 | change needing verification (any of the above) | implementer + cross-model judge per the `subagent-orchestration` Iron Law |
 
+## Per-slice tier inference (v1.5 — deterministic, task-TYPE-keyed)
+
+Once a slice is classified **delegable**, a second deterministic table infers
+its `model_tier` (road-to-cost-aware-model-routing, council 2026-07-08).
+Keyed **exclusively on the classifier's task-TYPE outputs** — never raw size
+metrics; diff size anti-correlates with difficulty in refactoring domains.
+
+```
+UNKNOWN / AMBIGUOUS → inherit (SESSION TIER). NEVER GUESS DOWN.
+SIZE SIGNALS ARE NEGATIVE GUARDS ONLY — THEY REVOKE A lite CANDIDACY,
+THEY NEVER CREATE ONE.
+```
+
+| Slice type (classifier output) | Inferred tier |
+|---|---|
+| Delegable + read-only fan-out (grep / inventory / discovery targets) | `lite` |
+| Delegable + mechanical / template-driven transform WITH test coverage | `lite` (verify-fail escalates to `medium` per the steering cascade) |
+| Delegable + mutating WITHOUT test coverage | `medium` |
+| Delegable + synthesis / judgment (review, analysis slice) | `medium` — judge one tier up per the orchestration Iron Law |
+| Any other / ambiguous shape | `inherit` — session tier, no downshift |
+
+**Negative size guard:** slice scope exceeding the mechanical envelope
+(multi-file mutation, diff surface beyond single responsibility) loses `lite`
+candidacy, resolves one row down — size never argues FOR a downshift, only
+against one.
+
+Every inferred decision records `tier_source: "inferred"` in orchestration
+telemetry (static pins record `"static"`; session-tier runs `"inherit"`) so
+the evidence gate scores inferred routing separately from static pinning.
+
 ## v2+ (deferred, gated on Phase 6 evidence)
 
 LLM-based classification — only if the deterministic rules prove too coarse

package/dist/agent-src/contexts/execution/orchestration-telemetry.md

@@ -19,7 +19,12 @@ v1 forward-compat rule on unknown fields).
   "wall_clock_ms": 0,
   "outcome": "DONE",
   "verify_mode": "deterministic",
-  "verdict_changed_outcome": null
+  "verdict_changed_outcome": null,
+  "task_class": null,
+  "tier_chosen": null,
+  "tier_source": null,
+  "escalated_from": null,
+  "verify_result_by_tier": null
 }
 ```
 
@@ -36,6 +41,15 @@ v1 forward-compat rule on unknown fields).
 | `outcome` | enum | One of `DONE` · `DONE_WITH_CONCERNS` · `NEEDS_CONTEXT` · `BLOCKED` · `killed`. |
 | `verify_mode` | enum | How output was verified: `deterministic` · `judge` · `none`. |
 | `verdict_changed_outcome` | bool \| null | **A3 extension (ADR-109 Track A).** For a review/verdict subagent (e.g. `production-validator`): did the verdict change the outcome vs the in-session baseline? `true` = caught a real issue the baseline missed / flipped a false `READY`→`NOT READY`; `false` = no lift; `null` = not a verdict dispatch / not measured. **Negative-control (clean single-file) tasks MUST record `false`** — a `true` on a control = spurious findings, fails Gate A. Additive field on THIS object, not a second schema. Boolean/counts only, no bodies. |
+| `task_class` | string \| null | **Routing extension (road-to-cost-aware-model-routing Phase 0).** Category id of the dispatched slice (e.g. `read-only-fanout`, `mechanical-edit`, `implementation`, `review-synthesis`). Enum-style id only, never free-form task text. `null` = pre-extension line / unclassified. |
+| `tier_chosen` | string \| null | Tier the slice was dispatched on (`lite` \| `medium` \| `high`). `null` = pre-extension line. |
+| `tier_source` | enum \| null | Where `tier_chosen` came from: `static` (frontmatter/category pin) · `inferred` (deterministic per-slice inference) · `inherit` (session tier — no downshift decision). Lets the evidence gate score inferred routing separately from static pinning. |
+| `escalated_from` | string \| null | When the slice re-dispatched after a verification failure: tier of the FAILED attempt (e.g. `lite` when a lite return failed verify and the slice re-ran on `medium`). `null` = no escalation. |
+| `verify_result_by_tier` | object \| null | Map tier → verification result per attempt of this slice (e.g. `{"lite":"fail","medium":"pass"}`). Values: `pass` \| `fail` \| `skipped`. Feeds the per-tier verify-pass-rate tripwire. Enums only, no verdict bodies. |
+
+All five routing fields are additive and optional — a line without them is
+still a valid orchestration line; readers ignore unknown fields per the v1
+forward-compat rule.
 
 ## Privacy floor
 

package/dist/agent-src/contexts/execution/subagent-steering.md

@@ -42,6 +42,38 @@ Only automatic response to a transient failure; structural/semantic errors (e.g.
 `BLOCKED` envelope) do **not** trigger a downshift — escalate to the orchestrator
 immediately.
 
+## Verify-fail escalation — the downshift cascade (M3)
+
+Cheap-first cascade for DOWNSHIFTED slices only
+(road-to-cost-aware-model-routing, council 2026-07-08). Transient failures
+(above) and verify-fails are distinct: transient retries downward once; a
+**verification failure escalates upward**.
+
+```
+VERIFY-FAIL ON A DOWNSHIFTED RETURN → RE-DISPATCH ONE TIER UP.
+COUNTS AGAINST THE EXISTING N=3 BUDGET — NEVER A NEW BUDGET.
+ATTEMPT 1 lite → ATTEMPT 2 medium → ATTEMPT 3 = SLICE FAILED,
+ORCHESTRATOR REPLANS AT SESSION TIER.
+ESCALATION TRIGGER IS THE JUDGE VERDICT / DETERMINISTIC VERIFY RESULT —
+NEVER THE SUBAGENT'S OWN CONFIDENCE.
+```
+
+- **Scope:** slices with `tier_source: static | inferred` only. `inherit`
+  slices keep existing same-tier retry semantics — no behavior change outside
+  the downshift path.
+- **Budget accounting:** each escalated attempt consumes one of the slice's
+  three attempts (`budgetHalt()` unchanged). Two failed attempts mark the
+  slice failed; the orchestrator replans — a slice's verify-fail never
+  poisons the orchestrator trajectory, only the final verified return (or
+  failure mark) enters its context.
+- **Telemetry:** the re-dispatch records `escalated_from: <failed tier>` and
+  appends to `verify_result_by_tier`.
+- **Economics guard:** a class escalating > 40% of the time is cheaper
+  started on the higher tier — the escalation-rate tripwire (below) promotes
+  its static default; the cascade is for the tail, not the norm.
+
+Deterministic reference: `escalateOnVerifyFail()`.
+
 ## Failure-type stop — the N=3 budget applied per subagent type
 
 Two consecutive **verification-failed** returns from one subagent type in a
@@ -88,6 +120,26 @@ The guardrail thresholds (`breachedGuardrails()`), read off the
 
 A breach is a maintainer/user signal, surfaced — never an automatic flip.
 
+## Cost-routing tripwires — steering policy for downshifted dispatch
+
+Two tripwires guard the cost-aware downshift path
+(road-to-cost-aware-model-routing, council 2026-07-08). Like the rollback
+guardrails they are **surfaced, never auto-flipped** — steering policy over
+the routing telemetry fields (`task_class`, `tier_chosen`, `escalated_from`,
+`verify_result_by_tier` in [`orchestration-telemetry`](orchestration-telemetry.md)),
+not a new mechanism:
+
+| Tripwire | Threshold | Action when fired |
+|---|---|---|
+| **Escalation-rate promotion** | per-class escalation rate > 40% over the rolling window | Class's default tier is wrong — cascading it costs more than starting high (decision-theoretic escalation analysis). Promote the class's static default one tier, log the promotion; do not keep cascading. |
+| **Verify-pass drift** | a tier's verify-pass rate drops below its trailing baseline | Verifier or model drift — a drifting verifier silently escalates everything (cost ~3x). Surface the drift with per-tier numbers; never silently absorb the extra escalations. |
+
+Deterministic references: `escalationPromotionCandidates()` and
+`verifyPassDrift()` over `readTierRoutingMetrics()` aggregates. Per-tier
+quality view (spend by tier, escalation count by class, verify-pass rate by
+tier) surfaces via `/cost:report` — the delayed-signal quality guard: cost
+dashboards alone look fine while quality regresses.
+
 ## Kill-switch
 
 ```
@@ -101,7 +153,8 @@ This is the canonical disable — no code change, effective on the next run.
 
 [`src/scripts/_lib/subagent_steering.ts`](../../../../src/scripts/_lib/subagent_steering.ts)
 (`isLayerDisabled`, `budgetHalt`, `typeStop`, `sliceDispatchAllowed`,
-`breachedGuardrails`), covered by
+`breachedGuardrails`, `readTierRoutingMetrics`,
+`escalationPromotionCandidates`, `verifyPassDrift`), covered by
 [`tests/scripts/_lib_subagent_steering.test.ts`](../../../../tests/scripts/_lib_subagent_steering.test.ts).
 
 ## Related

package/dist/agent-src/contexts/execution/toolchain-resolver.md

@@ -1,7 +1,7 @@
 # Toolchain Resolver Contract
 
 Loaded by every engineering command that runs tests or quality tools
-(`/tests execute`, `/tests create`, `/quality-fix`, `/review-changes`,
+(`/tests execute`, `/tests create`, `/fix quality`, `/review-changes`,
 `/work`). Holds the single source of truth for **stack-adaptive
 toolchain resolution**: detect the consumer's test runner / quality
 tools and run the right one — instead of a per-stack command explosion.

package/dist/agent-src/contexts/model-recommendations.md

@@ -39,6 +39,25 @@ tier is the reasoning band; `context: large` is the context-window need.
 | **Implementation after a `high`-tier plan** | `medium` | Plan is done, execution is mechanical |
 | **Trivial mechanical** (formatting, one-line config, rote rename) | `lite` | No reasoning required; fastest tier suffices |
 
+## Subagent Category → Tier Defaults (dispatch-time downshift)
+
+Normative defaults for DISPATCHED subagent slices (road-to-cost-aware-model-routing,
+council 2026-07-08). The orchestrator's own session model is never switched;
+these tiers apply to the sub-task the orchestrator spawns. Category-keyed —
+immune to per-instance misrouting; unknown/ambiguous category → `inherit`.
+
+| Subagent category | Tier | Why |
+|---|---|---|
+| Read-only fan-out (grep / inventory / file discovery) | `lite` | Returns get deterministic verification; quality risk ~0 by construction |
+| Mechanical single-file regen / template-driven transform | `lite`→`medium` fallback | Pattern application, no open-ended reasoning; verify-fail escalates one tier |
+| Implementation (bounded, planned slice) | `medium` | Plan exists; execution is pattern work |
+| Review / judge / synthesis / architecture | `medium`\|`high` | Reasoning depth is the product |
+
+**Judge asymmetry invariant:** the cross-model judge always runs one tier
+ABOVE the implementer tier (ladder in
+[`subagent-configuration`](subagent-configuration.md)). Downshifting an
+implementer never downshifts its judge.
+
 ## Detection Heuristics
 
 | Signal | Task Type | Tier |

package/dist/agent-src/contexts/skills-and-commands.md

@@ -60,7 +60,7 @@ Commands often chain together. Here are the main workflows:
 ### Quality & PR
 
 ```
-/quality-fix → /review-changes → /create-pr → /fix-pr-comments
+/fix quality → /review changes → /create-pr → /fix pr-comments
       ↓              ↓                ↓              ↓
   PHPStan/Rector  Self-review     Open PR       Address feedback
 ```
@@ -137,7 +137,7 @@ Commands often chain together. Here are the main workflows:
 | "Fix this issue" | `/bug-fix` |
 | "Create a PR" | `/create-pr` |
 | "CI is failing" | `/fix-ci` |
-| "Run quality checks" | `/quality-fix` |
+| "Run quality checks" | `/fix quality` |
 | "What's the status of this module?" | `/module-explore` |
 | "Document this area" | `/context-create` |
 | "Where was I?" | `/agent-handoff` (start fresh chat with context) |

package/dist/agent-src/contexts/subagent-configuration.md

@@ -25,6 +25,14 @@ If the session runs on **opus**, judge stays on opus (no higher tier
 available). If the session runs on **sonnet**, judge defaults to opus.
 If the session runs on **haiku**, judge defaults to sonnet.
 
+**Downshift never touches the judge.** When cost-aware routing runs an
+implementer on a downshifted tier (per the category → tier defaults in
+[`model-recommendations § Subagent Category → Tier Defaults`](model-recommendations.md)),
+the judge still resolves one tier above the IMPLEMENTER's resolved tier —
+a `lite` implementer gets at least a `medium` judge. Downshifting an
+implementer never downshifts its judge below what the verify contract
+requires; a judge is never `lite`.
+
 ## Resolution order
 
 For both implementer and judge:

package/dist/agent-src/rules/external-reference-deep-dive.md

@@ -64,7 +64,7 @@ User explicitly fences the scope (*"quick scan only"*, *"just glance at the READ
 
 ## See also
 
-- Command [`/analyze-reference-repo`](../commands/analyze-reference-repo.md) — canonical deep-dive flow.
+- Command [`/analyze-reference-repo`](../commands/analyze/reference-repo.md) — canonical deep-dive flow.
 - Rule [`think-before-action`](think-before-action.md) — sibling Iron Law for code paths in **this** repo; this rule is its mirror for **external** artifacts.
 - Rule [`ask-when-uncertain`](ask-when-uncertain.md) — when a fetch budget caps, ask which subtree to expand instead of guessing.
 - Skill [`markitdown`](../skills/markitdown/SKILL.md) — convert binary office formats before analysis.

package/dist/agent-src/skills/finishing-a-development-branch/SKILL.md

@@ -110,7 +110,7 @@ a different sub-procedure (steps 5a–5d).
 
 1. Ensure the branch is up to date with the base →
    [`prepare-for-review`](../../commands/prepare-for-review.md)
-2. Self-review the full diff → [`review-changes`](../../commands/review-changes.md)
+2. Self-review the full diff → [`review-changes`](../../commands/review/changes.md)
 3. Write the PR description → [`create-pr-description`](../../commands/create-pr/description-only.md)
 4. Open the PR → [`create-pr`](../../commands/create-pr.md)
 5. Confirm the PR opened green, not red
@@ -231,7 +231,7 @@ After the chosen option completes, report:
 * Writing the commit for any last-minute tweaks →
   [`commit`](../../commands/commit.md),
   [`conventional-commits-writing`](../conventional-commits-writing/SKILL.md)
-* Self-review walkthrough → [`review-changes`](../../commands/review-changes.md)
+* Self-review walkthrough → [`review-changes`](../../commands/review/changes.md)
 * Creating the PR → [`create-pr`](../../commands/create-pr.md)
 * Processing review comments after the PR is open →
   [`receiving-code-review`](../receiving-code-review/SKILL.md)

package/dist/agent-src/skills/judge-artifact-completeness/SKILL.md

@@ -132,5 +132,5 @@ Anti-length: fixtures include `SHORT_COMPLETE` (short, all dimensions) and `LONG
 ## References
 
 - Sibling judges: [`judge-code-quality`](../judge-code-quality/SKILL.md), [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md), [`judge-security-auditor`](../judge-security-auditor/SKILL.md), [`judge-test-coverage`](../judge-test-coverage/SKILL.md).
-- Dispatchers: [`/refine-ticket`](../../commands/refine-ticket.md), [`/adr-create`](../../commands/adr-create.md), [`/review-changes`](../../commands/review-changes.md).
+- Dispatchers: [`/refine-ticket`](../../commands/refine-ticket.md), [`/adr-create`](../../commands/adr-create.md), [`/review-changes`](../../commands/review/changes.md).
 - Rubric schemas: `rubrics/roadmap-score.json`, `rubrics/pr-review-score.json`, `rubrics/architecture-score.json`, `rubrics/ticket-quality-score.json`.

package/dist/agent-src/skills/judge-bug-hunter/SKILL.md

@@ -159,4 +159,4 @@ the endpoint with an empty body") — the judge does not execute tools.
 - [`judge-security-auditor`](../judge-security-auditor/SKILL.md),
   [`judge-test-coverage`](../judge-test-coverage/SKILL.md),
   [`judge-code-quality`](../judge-code-quality/SKILL.md) — sibling
-  judges dispatched together by [`/review-changes`](../../commands/review-changes.md).
+  judges dispatched together by [`/review-changes`](../../commands/review/changes.md).

package/dist/agent-src/skills/judge-code-quality/SKILL.md

@@ -160,4 +160,4 @@ for the implementer — the judge does not execute tools.
 - Sibling judges: [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md),
   [`judge-security-auditor`](../judge-security-auditor/SKILL.md),
   [`judge-test-coverage`](../judge-test-coverage/SKILL.md) — dispatched
-  together by [`/review-changes`](../../commands/review-changes.md).
+  together by [`/review-changes`](../../commands/review/changes.md).

package/dist/agent-src/skills/judge-security-auditor/SKILL.md

@@ -170,4 +170,4 @@ Runtime boundary: the judge does not execute tools.
 - Sibling judges: [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md),
   [`judge-test-coverage`](../judge-test-coverage/SKILL.md),
   [`judge-code-quality`](../judge-code-quality/SKILL.md) — dispatched
-  together by [`/review-changes`](../../commands/review-changes.md).
+  together by [`/review-changes`](../../commands/review/changes.md).

package/dist/agent-src/skills/judge-synthesis/SKILL.md

@@ -130,5 +130,5 @@ Required fields (ordered):
 
 - Code judges: [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md), [`judge-code-quality`](../judge-code-quality/SKILL.md), [`judge-security-auditor`](../judge-security-auditor/SKILL.md), [`judge-test-coverage`](../judge-test-coverage/SKILL.md), [`architecture-review-lens`](../architecture-review-lens/SKILL.md).
 - Artifact / defence judges: [`judge-artifact-completeness`](../judge-artifact-completeness/SKILL.md), [`judge-injection-defense`](../judge-injection-defense/SKILL.md).
-- Dispatchers that feed this: [`/review-changes`](../../commands/review-changes.md) (5 code judges), [`subagent-orchestration`](../subagent-orchestration/SKILL.md) (parallel judge fan-out).
+- Dispatchers that feed this: [`/review-changes`](../../commands/review/changes.md) (5 code judges), [`subagent-orchestration`](../subagent-orchestration/SKILL.md) (parallel judge fan-out).
 - **LLM-as-a-Judge** — Zheng et al. (2023), [arxiv.org/abs/2306.05685](https://arxiv.org/abs/2306.05685); the consolidation layer over the specialized-judge pattern, with consensus/conflict surfacing instead of a single aggregate score.

package/dist/agent-src/skills/judge-test-coverage/SKILL.md

@@ -159,4 +159,4 @@ as a follow-up for the implementer — the judge does not execute tools.
 - Sibling judges: [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md),
   [`judge-security-auditor`](../judge-security-auditor/SKILL.md),
   [`judge-code-quality`](../judge-code-quality/SKILL.md) — dispatched
-  together by [`/review-changes`](../../commands/review-changes.md).
+  together by [`/review-changes`](../../commands/review/changes.md).

package/dist/agent-src/skills/markitdown/SKILL.md

@@ -217,7 +217,7 @@ Converted Markdown is **adversarial input**. A PDF with the literal string "igno
 **WHEN NOT to use this**
 
 - Source is plain text, Markdown, JSON, YAML, or source code — read directly, no conversion needed.
-- Source is a remote repo to be analyzed — route to the [`analyze-reference-repo`](../../commands/analyze-reference-repo.md) command, which composes this skill for non-text artefacts.
+- Source is a remote repo to be analyzed — route to the [`analyze-reference-repo`](../../commands/analyze/reference-repo.md) command, which composes this skill for non-text artefacts.
 - Source is a screenshot to be visually compared — route to a vision-first skill, not a text-extraction skill.
 
 ## When the agent should load this

package/dist/agent-src/skills/mobile-e2e-strategy/SKILL.md

@@ -18,7 +18,7 @@ packs:
 - Planning iOS Simulator / Android Emulator coverage in CI (cost, runner type, parallelism).
 - Triaging flaky mobile tests that span the simulator/emulator boundary.
 - Bridging mobile E2E results into the same review surface as web E2E
-  (`playwright-testing`, `e2e-plan`, `e2e-heal`).
+  (`playwright-testing`, `/tests e2e-plan`, `/tests e2e-heal`).
 
 **This skill selects and plans — it does not generate test code.** For the chosen framework, apply its own conventions; for the host environment, see the cross-links below.
 
@@ -27,8 +27,8 @@ packs:
 - `react-native-setup` — RN/Expo environment, Xcode/Android Studio, EAS Build.
 - `docs/guidelines/agent-infra/ios-simulator-guide.md` — `simctl` / `idb` / accessibility-driven testing on iOS.
 - `playwright-testing` — web E2E baseline (do **not** reuse for native mobile).
-- `e2e-plan` — explore an app and produce an E2E plan in Markdown.
-- `e2e-heal` — debug and fix failing E2E tests.
+- `/tests e2e-plan` — explore an app and produce an E2E plan in Markdown.
+- `/tests e2e-heal` — debug and fix failing E2E tests.
 
 ## Procedure
 
@@ -115,8 +115,8 @@ without leaving the review.
 ## Bridging to the existing E2E surface
 
 - **Web + mobile in one repo:** keep Playwright for web, add a separate `mobile/` suite using Detox or Maestro. Do **not** force-fit Playwright onto native UI.
-- **Plan reuse:** the planning patterns in `e2e-plan` (user journeys, test pyramid placement, stable selectors) apply unchanged. The implementation lives in the mobile framework.
-- **Heal reuse:** the diagnostic loop in `e2e-heal` (reproduce → isolate → minimal fix → verify) applies. Replace browser-specific tooling with mobile-framework equivalents (Detox `--loglevel verbose`, Maestro Studio replays, Appium Inspector).
+- **Plan reuse:** the planning patterns in `/tests e2e-plan` (user journeys, test pyramid placement, stable selectors) apply unchanged. The implementation lives in the mobile framework.
+- **Heal reuse:** the diagnostic loop in `/tests e2e-heal` (reproduce → isolate → minimal fix → verify) applies. Replace browser-specific tooling with mobile-framework equivalents (Detox `--loglevel verbose`, Maestro Studio replays, Appium Inspector).
 - **Selectors:** prefer accessibility identifiers (`accessibilityIdentifier` on iOS, `contentDescription` on Android) over coordinate taps — see `ios-simulator-guide.md` Module 1.
 
 ## Output format

package/dist/agent-src/skills/prompt-optimizer/SKILL.md

@@ -17,7 +17,7 @@ packs:
 
 - The user pastes a rough prompt and asks for it to be optimized, rewritten, sharpened, or "made better".
 - The user mentions a target AI (ChatGPT, Claude, Gemini, Perplexity, Copilot) and wants their prompt tuned for it.
-- The user invokes [`/optimize-prompt`](../../commands/optimize-prompt.md).
+- The user invokes [`/optimize-prompt`](../../commands/optimize/prompt.md).
 - The user describes a goal ("I need a marketing-email prompt for ChatGPT") and the deliverable is a prompt, not the email itself.
 
 ## When NOT to use (near-misses)
@@ -27,7 +27,7 @@ packs:
 | "refine this ticket / prompt for the engine" | [`refine-prompt`](../refine-prompt/SKILL.md) |
 | "make this skill description pushier" | [`description-assist`](../description-assist/SKILL.md) |
 | "write the marketing email itself" | direct execution — the user wants the artifact, not a prompt |
-| "review my code / commit" | [`review-changes`](../../commands/review-changes.md) and friends |
+| "review my code / commit" | [`review-changes`](../../commands/review/changes.md) and friends |
 
 ## The 4-D Methodology
 

package/dist/agent-src/skills/quality-tools/SKILL.md

@@ -35,7 +35,7 @@ Toolchains differ per language and project, often unknown to the agent —
 discovery + execution burns time and tokens. Under the default, exactly
 three triggers justify running a quality tool:
 
-1. **Explicit ask this turn** — user says so or invokes `/quality-fix`.
+1. **Explicit ask this turn** — user says so or invokes `/fix quality`.
 2. **Concrete CI failure** — remote pipeline reports a failing check;
    run exactly that failing check to reproduce and fix (`/fix:ci` is
    the canonical flow).

package/dist/agent-src/skills/repomix-packer/SKILL.md

@@ -99,7 +99,7 @@ If Secretlint flags anything, STOP — sanitize the input or add the offending p
 Most workflows that call this skill pass the snapshot to:
 
 - A code-review pass — pair with [`judge-bug-hunter`](../judge-bug-hunter/SKILL.md) or [`judge-security-auditor`](../judge-security-auditor/SKILL.md).
-- Reference-repo analysis — route to [`analyze-reference-repo`](../../commands/analyze-reference-repo.md).
+- Reference-repo analysis — route to [`analyze-reference-repo`](../../commands/analyze/reference-repo.md).
 - Migration scoping — route to [`blast-radius-analyzer`](../blast-radius-analyzer/SKILL.md).
 
 Cite the snapshot path so the consumer skill can read it.

package/dist/agent-src/skills/requesting-code-review/SKILL.md

@@ -64,7 +64,7 @@ Before asking anyone else:
 * If you find issues → fix them, do **not** ship them and hope the
   reviewer flags them
 
-Use the [`review-changes`](../../commands/review-changes.md) command
+Use the [`review-changes`](../../commands/review/changes.md) command
 as the structured walk-through.
 
 ### 2. Establish the diff baseline
@@ -185,7 +185,7 @@ When handing the review request to the reviewer (PR body, Slack, email):
 
 ## When to hand over to another skill / command
 
-* Self-review walkthrough → [`review-changes`](../../commands/review-changes.md)
+* Self-review walkthrough → [`review-changes`](../../commands/review/changes.md)
 * Bringing a stacked branch up to date first →
   [`prepare-for-review`](../../commands/prepare-for-review.md)
 * Writing the PR description → [`create-pr-description`](../../commands/create-pr-description.md)

package/dist/agent-src/skills/verify-repair-loop/SKILL.md

@@ -34,7 +34,7 @@ Do NOT use when:
   [`subagent-orchestration`](../subagent-orchestration/SKILL.md) (judge reads the
   diff, sovereign).
 * Only a **one-shot** multi-judge review of a finished diff →
-  [`/review-changes`](../../commands/review-changes.md).
+  [`/review-changes`](../../commands/review/changes.md).
 * Verdict must come from a **live app** (Playwright vs running services) →
   **deferred** (see Scope); use test/quality verdicts until that trigger fires.
 
@@ -200,7 +200,7 @@ iter2 fixes A, breaks B, 92% → "PASS"      ✗ regression ignored
 
 * [`subagent-orchestration`](../subagent-orchestration/SKILL.md) — `do-and-judge`
   (judge-sovereign, diff-read) is the sibling; this skill is test-verdict-gated.
-* [`/review-changes`](../../commands/review-changes.md) — one-shot multi-judge
+* [`/review-changes`](../../commands/review/changes.md) — one-shot multi-judge
   review; wires this loop as an opt-in step.
 * [`playwright-testing`](../playwright-testing/SKILL.md),
   [`quality-tools`](../quality-tools/SKILL.md) — verdict sources.

package/dist/agent-src/templates/agent-settings.md

@@ -276,7 +276,7 @@ quality:
   # false = default. Agent NEVER runs quality tools / full test suites
   #         proactively — and does not ask. The user runs them manually;
   #         remote CI is the authoritative gate. The agent runs one ONLY
-  #         on: (1) explicit ask this turn (e.g. /quality-fix), (2) a
+  #         on: (1) explicit ask this turn (e.g. /fix quality), (2) a
   #         concrete CI failure — run exactly that failing check, or
   #         (3) the new-gate carve-out below.
   # true  = opt-in legacy: agent runs the quality pipeline whenever

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.ts (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "8.4.1"
+agent_config_version: "8.6.0"
 
 # --- Project identity ---
 project:
@@ -200,7 +200,7 @@ ghostwriter:
 
 # --- Quality pipeline (optional) ---
 #
-# Per-language gate tools the `quality-fix` command invokes. Empty
+# Per-language gate tools the `/fix quality` command invokes. Empty
 # list = skip the language. Agent will still auto-detect; these
 # values are advisory.
 quality:

package/dist/agent-src/templates/scripts/work_engine/stack/runner.ts

@@ -11,7 +11,7 @@
  * runner and quality tools does this stack actually use, and what is the
  * exact command to invoke them?* It is the engine behind 6.1.0 Step 6 — the
  * toolchain resolver that lets one set of commands (`/tests execute`,
- * `/tests create`, `/quality-fix`, `/review-changes`, `/work`) adapt to
+ * `/tests create`, `/fix quality`, `/review changes`, `/work`) adapt to
  * phpunit / pest / vitest / jest / playwright / pytest / go / cargo instead
  * of exploding into per-stack command variants.
  *