@event4u/agent-config 1.15.0 → 1.17.0

package/.agent-src/commands/council.md

@@ -0,0 +1,54 @@
+---
+name: council
+description: Council orchestrator — routes to default, pr, design, optimize
+cluster: council
+disable-model-invocation: true
+suggestion:
+  eligible: true
+  trigger_description: "external second opinion, cross-AI review, devil's advocate on a plan/roadmap/diff, council on PR/design/optimize, polling another model"
+  trigger_context: "user wants an outside critique on an artefact (roadmap, diff, prompt, files, PR, design doc, optimization target) without polluting the reviewer with the host agent's framing"
+---
+
+# /council
+
+Top-level orchestrator for the `/council` family. Replaces 4 standalone
+commands with a single entry point + sub-command dispatch. Each lens
+shares the same transport, neutrality preamble, and cost gate; the
+sub-command swaps the mode-specific addendum.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/council default` | `commands/council/default.md` | Generic neutral lens — prompt, roadmap, diff, or files |
+| `/council pr` | `commands/council/pr.md` | Pull a GitHub PR via `gh` and run the council on the diff with PR-specific framing |
+| `/council design` | `commands/council/design.md` | Run the council on a design doc / ADR / architecture proposal |
+| `/council optimize` | `commands/council/optimize.md` | Run the council on an optimization target — ranked, evidence-based suggestions |
+
+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: `/council <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the routed file and follow its `## Instructions` section
+   verbatim with the remaining args.
+4. If the sub-command is unknown or missing, print the table above and ask:
+
+   > 1. default — neutral lens on a prompt / roadmap / diff / files
+   > 2. pr — review a GitHub PR (read-only by default)
+   > 3. design — review a design doc / ADR / architecture proposal
+   > 4. optimize — ranked, evidence-based optimization advice
+
+## Rules
+
+- **Do NOT commit, push, or open a PR** unless the sub-command explicitly
+  authorizes it. The PR sub-command can post **one** comment per
+  invocation, opt-in only.
+- **Do NOT chain sub-commands.** One `/council <sub>` per turn.
+- **Hard floor — text only.** `/council` produces text and (under
+  `pr` with explicit opt-in) one PR comment. It does NOT edit files,
+  approve / merge PRs, or run optimizations.
+- If the user invokes `/council` with no argument, **show the menu** —
+  do not guess which sub-command they meant.

package/.agent-src/commands/{create-pr-description.md → create-pr/description-only.md}

@@ -1,5 +1,7 @@
 ---
-name: create-pr-description
+name: create-pr:description-only
+cluster: create-pr
+sub: description-only
 skills: [git-workflow]
 description: Generate a PR description as a copyable markdown block — used standalone or by create-pr
 disable-model-invocation: true
@@ -9,7 +11,7 @@ suggestion:
   trigger_context: "PR exists or branch ready for review without description"
 ---
 
-# create-pr-description
+# /create-pr:description-only
 
 ## Input
 

package/.agent-src/commands/create-pr.md

@@ -1,5 +1,6 @@
 ---
 name: create-pr
+cluster: create-pr
 skills: [git-workflow]
 description: Create a GitHub PR with structured description from Jira ticket and code changes
 disable-model-invocation: true
@@ -9,11 +10,31 @@ suggestion:
   trigger_context: "branch is ahead of base and not yet on a PR"
 ---
 
-# create-pr
+# /create-pr
 
-Uses `/create-pr-description` to generate the PR content, then creates the PR via GitHub API.
+Top-level entry point for the `/create-pr` family. Bare `/create-pr`
+runs the full create-PR flow described below. The `:description-only`
+sub-command produces a copyable PR description without creating the PR.
 
-## Instructions
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/create-pr` (bare) | this file (`## Default flow`) | Full flow — generate description, push, create PR |
+| `/create-pr:description-only` | `commands/create-pr/description-only.md` | Generate the PR description as a copyable markdown block, no PR creation |
+
+## Dispatch
+
+1. Parse the user's argument: `/create-pr[:<sub>] [args]`.
+2. Bare `/create-pr` → run the `## Default flow` below verbatim.
+3. `/create-pr:description-only` → load
+   `commands/create-pr/description-only.md` and follow its
+   `## Instructions` section verbatim.
+4. Unknown sub-command → print the table above and ask which one.
+
+## Default flow
+
+Uses `/create-pr:description-only` to generate the PR content, then creates the PR via GitHub API.
 
 ### 1. Check prerequisites
 
@@ -24,15 +45,38 @@ Uses `/create-pr-description` to generate the PR content, then creates the PR vi
 
 ### 2. Generate PR content
 
-Run `/create-pr-description` to generate the PR title and body.
+Run `/create-pr:description-only` to generate the PR title and body.
 This handles: Jira ticket extraction, diff analysis, commit messages, **PR template filling**.
 
 **CRITICAL**: The PR body MUST use the project's PR template (`.github/pull_request_template.md`).
 Read the template file and fill in its sections. If the template does not exist, use the
-fallback structure defined in `/create-pr-description`. NEVER invent a custom body structure.
+fallback structure defined in `/create-pr:description-only`. NEVER invent a custom body structure.
 
 The user reviews and adjusts the content in that step.
 
+### 2b. Offer council review (B2 hook)
+
+If `.agent-settings.yml` has `ai_council.enabled: true` **and** at least
+one member is enabled, ask (in the user's language):
+
+> 1. Run the council on this diff before opening the PR? (billable)
+> 2. Skip council review
+
+Suppress when `personal.autonomy: on` (council is billable; autonomy
+must not silently spend — see `road-to-ai-council.md` Decision 3).
+
+If picked **1**:
+
+- Compute the diff range — `origin/<default>..HEAD` from step 1.
+- Run `/council diff:<base>..<head>` with `original_ask` set to the
+  PR title from step 2 (the user's framing of the change).
+- Surface findings to the user before step 3. **Do not** auto-edit
+  the PR body or block PR creation — output is advisory.
+- Optional: offer to append a one-paragraph "Council notes" section
+  to the PR description for reviewer transparency. Default: skip.
+
+If picked **2** → continue.
+
 ### 3. Create the PR
 
 Once the user approves the content from step 2:

package/.agent-src/commands/e2e-heal.md

@@ -21,7 +21,7 @@ suggestion:
 > 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: `.augment/guidelines/e2e/playwright.md`
+- Read the Playwright guideline: `../../docs/guidelines/e2e/playwright.md`
 
 ### 2. Run failing tests
 

package/.agent-src/commands/e2e-plan.md

@@ -21,7 +21,7 @@ suggestion:
 > 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: `.augment/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/.agent-src/commands/{feature-dev.md → feature/dev.md}

@@ -1,5 +1,7 @@
 ---
-name: feature-dev
+name: feature:dev
+cluster: feature
+sub: dev
 description: Full 7-phase feature development workflow for complex features.
 skills: [laravel, php-coder]
 disable-model-invocation: true
@@ -8,13 +10,14 @@ suggestion:
   trigger_description: "build this feature end-to-end, run the full feature workflow"
   trigger_context: "long-form feature description spanning multiple components"
 ---
-# /feature-dev
+
+# /feature:dev
 
 > Full 7-phase feature development workflow for complex features.
 
 ## Trigger
 
-`/feature-dev {description}` or `/feature-dev` (interactive)
+`/feature:dev {description}` or `/feature:dev` (interactive)
 
 ## When to use
 

package/.agent-src/commands/{feature-explore.md → feature/explore.md}

@@ -1,5 +1,7 @@
 ---
-name: feature-explore
+name: feature:explore
+cluster: feature
+sub: explore
 skills: [laravel]
 description: Brainstorm and explore a feature idea before committing to a full plan
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "open-ended feature idea without acceptance criteria"
 ---
 
-# feature-explore
-
+# /feature explore
 ## Instructions
 
 This is a **lightweight, conversational** exploration — no structured output yet.
@@ -181,4 +182,4 @@ What's next?
 
 ## See also
 
-- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#po) — PO mode output contract (Goal / Assumptions / Acceptance criteria / Impacted modules / Risks / Open questions for stakeholder)
+- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#po) — PO mode output contract (Goal / Assumptions / Acceptance criteria / Impacted modules / Risks / Open questions for stakeholder)

package/.agent-src/commands/{feature-plan.md → feature/plan.md}

@@ -1,5 +1,7 @@
 ---
-name: feature-plan
+name: feature:plan
+cluster: feature
+sub: plan
 skills: [feature-planning]
 description: Interactively plan a feature — research, discuss, and create a structured feature document
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "feature idea referenced and no plan doc exists"
 ---
 
-# feature-plan
-
+# /feature plan
 ## Instructions
 
 ### 1. Gather the idea
@@ -111,7 +112,7 @@ Before asking detailed questions, **proactively research**:
   `status: active` is a binding constraint — propose structure that
   respects it. If the feature needs to contradict an ADR, surface that
   as a decision for the user before drafting the plan. See
-  [`engineering-memory-data-format`](../guidelines/agent-infra/engineering-memory-data-format.md).
+  [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md).
 
 **Share key findings with the user** — this informs the discussion:
 
@@ -208,6 +209,32 @@ Mir sind noch ein paar offene Fragen aufgefallen:
 Hast du dazu schon eine Meinung?
 ```
 
+### 5d. Offer council idea-validation (B4 hook)
+
+Once the conversation has converged on a problem statement, proposal,
+and rough scope (rounds 1–4), but **before** step 6 writes the file,
+ask (in the user's language):
+
+> 1. Run the council on this idea before writing the plan? (billable)
+> 2. Skip — write the plan now
+
+Suppress when `personal.autonomy: on` (council is billable).
+
+If picked **1**:
+
+- Build a short prompt: the problem, the proposal, the scope, the
+  open questions from round 4. **Do not** include the agent's
+  framing or recommendations — neutrality preamble is mandatory.
+- Run `/council prompt:"<assembled prompt>"` with `original_ask` set
+  to the feature title from step 1.
+- Surface convergent + divergent points back to the user. **Do not**
+  rewrite the proposal autonomously; let the user decide which
+  council points to fold in.
+- After the user has reviewed, return to step 6 with the (possibly
+  updated) proposal.
+
+If picked **2** → continue.
+
 ### 6. Create the feature document
 
 - Read `.augment/templates/features.md` for the structure.
@@ -287,6 +314,6 @@ What's next?
 
 ## See also
 
-- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#po) — PO mode output contract (Goal / Assumptions / Acceptance criteria / Impacted modules / Risks / Open questions for stakeholder)
+- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#po) — PO mode output contract (Goal / Assumptions / Acceptance criteria / Impacted modules / Risks / Open questions for stakeholder)
 - [`refine-ticket`](refine-ticket.md) — optional upstream step: run first when the input is a Jira/Linear ticket rather than a fresh idea
 - [`estimate-ticket`](estimate-ticket.md) — sibling of `refine-ticket`; size + risk + split recommendation for an already-refined ticket

package/.agent-src/commands/{feature-refactor.md → feature/refactor.md}

@@ -1,5 +1,7 @@
 ---
-name: feature-refactor
+name: feature:refactor
+cluster: feature
+sub: refactor
 skills: [laravel, php-coder]
 description: Refine and update an existing feature plan through interactive discussion
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "existing agents/features/*.md referenced in the prompt"
 ---
 
-# feature-refactor
-
+# /feature refactor
 ## Instructions
 
 ### 1. Find the feature

package/.agent-src/commands/{feature-roadmap.md → feature/roadmap.md}

@@ -1,5 +1,7 @@
 ---
-name: feature-roadmap
+name: feature:roadmap
+cluster: feature
+sub: roadmap
 skills: [agent-docs-writing]
 description: Generate implementation roadmap(s) from a feature plan and link them
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "existing feature plan without linked roadmap"
 ---
 
-# feature-roadmap
-
+# /feature roadmap
 ## Instructions
 
 ### 1. Find the feature
@@ -42,7 +43,7 @@ Stop.
 ### 2. Analyze the feature
 
 - Read the feature file completely.
-- Read `agents/roadmaps/template.md` for the roadmap structure.
+- Read the roadmap template at `.augment/templates/roadmaps.md` for the structure.
 - Research the codebase for affected areas mentioned in the feature.
 
 Determine how many roadmaps are needed:
@@ -180,11 +181,11 @@ What's next?
   requested them. See [`commit-policy`](../rules/commit-policy.md#never-write-commit-steps-into-roadmaps-unsolicited).
 - **Do NOT modify the feature plan** beyond updating the Roadmaps section and status.
 - **Always link roadmaps back to the feature** and vice versa.
-- **Use the roadmap template** from `agents/roadmaps/template.md`.
+- **Use the roadmap template** at `.augment/templates/roadmaps.md`.
 - **Reference specific files** in roadmap tasks — not vague descriptions.
 - **Include quality gates** (PHPStan, Rector, tests) in every phase.
 - **Research the codebase** to make tasks concrete and realistic.
 
 ## See also
 
-- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#planner) — Planner mode output contract (Goal / Constraints / Option set / Recommendation / Dependencies / Rollback)
+- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#planner) — Planner mode output contract (Goal / Constraints / Option set / Recommendation / Dependencies / Rollback)

package/.agent-src/commands/feature.md

@@ -0,0 +1,52 @@
+---
+name: feature
+description: Feature orchestrator — routes to explore, plan, refactor, roadmap, dev
+cluster: feature
+disable-model-invocation: true
+suggestion:
+  eligible: true
+  trigger_description: "explore feature idea, plan a feature, refactor feature plan, roadmap a feature, full feature dev"
+  trigger_context: "user starting or iterating on a feature workflow"
+---
+
+# /feature
+
+Top-level orchestrator for the `/feature` family. Replaces 5 standalone
+commands with a single entry point + sub-command dispatch.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/feature explore` | `commands/feature/explore.md` | Brainstorm an idea before committing to a plan |
+| `/feature plan` | `commands/feature/plan.md` | Interactively plan a feature, produce a structured plan doc |
+| `/feature refactor` | `commands/feature/refactor.md` | Refine and update an existing feature plan |
+| `/feature roadmap` | `commands/feature/roadmap.md` | Generate implementation roadmap(s) from a plan |
+| `/feature dev` | `commands/feature/dev.md` | Full 7-phase feature development workflow (heavyweight) |
+
+## Workflow ordering
+
+Typical sequence: `explore` → `plan` → `roadmap` → `dev` (or per-step
+implementation). Use `refactor` whenever an existing plan needs an update.
+
+## Dispatch
+
+1. Parse the user's argument: `/feature <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the corresponding `commands/feature/<sub>.md` file and
+   follow its `## Instructions` (or `## Steps`) section verbatim.
+4. If the sub-command is unknown or missing, print the menu and ask:
+
+   > 1. explore — brainstorm a feature idea
+   > 2. plan — produce a structured feature plan
+   > 3. refactor — update an existing feature plan
+   > 4. roadmap — generate roadmap(s) from a plan
+   > 5. dev — run the full 7-phase development workflow
+
+## Rules
+
+- **Do NOT chain sub-commands.** One `/feature <sub>` per turn — except
+  the agent may suggest the next logical sub-command at the end of a step
+  (numbered options per `user-interaction`).
+- If the user invokes `/feature` with no argument, **show the menu** — do
+  not guess which sub-command they meant.

package/.agent-src/commands/{fix-ci.md → fix/ci.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-ci
+name: fix:ci
+cluster: fix
+sub: ci
 skills: [github-ci, quality-tools]
 description: Fetch CI errors from GitHub Actions and fix them
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "open PR with failing checks"
 ---
 
-# fix-ci
-
+# /fix ci
 ## Instructions
 
 ### 1. Identify the failing CI run

package/.agent-src/commands/{fix-portability.md → fix/portability.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-portability
+name: fix:portability
+cluster: fix
+sub: portability
 description: Find and fix project-specific references in shared .augment/ package files
 disable-model-invocation: true
 suggestion:
@@ -7,8 +9,7 @@ suggestion:
   rationale: "Package-internal — only the event4u/agent-config repo runs this."
 ---
 
-# fix-portability
-
+# /fix portability
 ## Instructions
 
 ### 1. Run the portability checker

package/.agent-src/commands/{fix-pr-bot-comments.md → fix/pr-bots.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-pr-bot-comments
+name: fix:pr-bots
+cluster: fix
+sub: pr-bots
 skills: [php-coder, quality-tools]
 description: Fix and reply to bot review comments (Copilot, Augment, Greptile, etc.) on a GitHub PR
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "open PR with bot review comments unresolved"
 ---
 
-# fix-pr-bot-comments
-
+# /fix pr-bots
 ## Input
 
 The user may or may not provide a PR URL.

package/.agent-src/commands/{fix-pr-developer-comments.md → fix/pr-developers.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-pr-developer-comments
+name: fix:pr-developers
+cluster: fix
+sub: pr-developers
 skills: [php-coder]
 description: Fix and reply to human reviewer comments on a GitHub PR
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "open PR with unresolved human-reviewer comments"
 ---
 
-# fix-pr-developer-comments
-
+# /fix pr-developers
 ## Input
 
 The user may or may not provide a PR URL.

package/.agent-src/commands/{fix-pr-comments.md → fix/pr.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-pr-comments
+name: fix:pr
+cluster: fix
+sub: pr
 skills: [php-coder]
 description: Fix and reply to all open review comments (bots + human reviewers) on a GitHub PR
 disable-model-invocation: true
@@ -9,9 +11,8 @@ suggestion:
   trigger_context: "open PR with unresolved comments (bot + human)"
 ---
 
-# fix-pr-comments
-
-This command runs `fix-pr-bot-comments` and `fix-pr-developer-comments` in sequence on the same PR.
+# /fix pr
+This command runs `/fix pr-bots` and `/fix pr-developers` in sequence on the same PR.
 
 ## Input
 
@@ -44,14 +45,14 @@ The chosen mode applies to **both** phases.
 
 ### Phase 1: Bot comments
 
-Follow the full `fix-pr-bot-comments` instructions (see `.augment/commands/fix-pr-bot-comments.md`).
+Follow the full `/fix pr-bots` instructions (see `commands/fix/pr-bots.md`).
 Use the already-confirmed PR and mode — do not ask again.
 
 Report when done: "Bot comments done. Continuing with reviewer comments..."
 
 ### Phase 2: Developer comments
 
-Follow the full `fix-pr-developer-comments` instructions (see `.augment/commands/fix-pr-developer-comments.md`).
+Follow the full `/fix pr-developers` instructions (see `commands/fix/pr-developers.md`).
 Use the same PR and mode.
 
 ### After both phases

package/.agent-src/commands/{fix-references.md → fix/refs.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-references
+name: fix:refs
+cluster: fix
+sub: refs
 description: Find and fix broken cross-references in .augment/ and agents/ files
 disable-model-invocation: true
 suggestion:
@@ -7,8 +9,7 @@ suggestion:
   rationale: "Package-internal — only the event4u/agent-config repo runs this."
 ---
 
-# fix-references
-
+# /fix refs
 ## Instructions
 
 ### 1. Run the reference checker

package/.agent-src/commands/{fix-seeder.md → fix/seeder.md}

@@ -1,5 +1,7 @@
 ---
-name: fix-seeder
+name: fix:seeder
+cluster: fix
+sub: seeder
 skills: [eloquent]
 description: Scan seeder data files for broken foreign key references — find constants used without getReference() and fix them
 disable-model-invocation: true
@@ -9,8 +11,7 @@ suggestion:
   trigger_context: "seeder error output or recent edits in database/seeders/"
 ---
 
-# fix-seeder
-
+# /fix seeder
 Scans all `PhpDataSeeder` data files for foreign key references that use raw seeder constants
 instead of `getReference()`. Raw constants don't trigger lazy initialization of the referenced
 seeder, causing "items not available" errors when seeders run in unpredictable order.

package/.agent-src/commands/fix.md

@@ -0,0 +1,54 @@
+---
+name: fix
+description: Fix orchestrator — routes to ci, references, portability, seeder, pr-comments, pr-bot-comments, pr-developer-comments
+cluster: fix
+disable-model-invocation: true
+suggestion:
+  eligible: true
+  trigger_description: "fix CI, fix references, fix the broken seeder, fix PR comments, address bot review"
+  trigger_context: "user wants to fix something that has a dedicated sub-command"
+---
+
+# /fix
+
+Top-level orchestrator for the `/fix` family. Replaces 7 standalone commands
+with a single entry point + sub-command dispatch.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/fix ci` | `commands/fix/ci.md` | Fetch CI errors from GitHub Actions and fix them |
+| `/fix refs` | `commands/fix/refs.md` | Find and fix broken cross-references in `.augment/` and `agents/` |
+| `/fix portability` | `commands/fix/portability.md` | Find and fix project-specific references in shared `.augment/` files |
+| `/fix seeder` | `commands/fix/seeder.md` | Scan seeder data files for broken FK references |
+| `/fix pr` | `commands/fix/pr.md` | Fix and reply to **all** open review comments (bots + humans) |
+| `/fix pr-bots` | `commands/fix/pr-bots.md` | Fix and reply to **bot** review comments only |
+| `/fix pr-developers` | `commands/fix/pr-developers.md` | Fix and reply to **human** reviewer comments only |
+
+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: `/fix <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the routed file and follow its `## Instructions` section
+   verbatim with the remaining args.
+4. If the sub-command is unknown or missing, print the table above and ask:
+
+   > 1. ci — fetch and fix GitHub Actions errors
+   > 2. refs — fix broken cross-refs in agent docs
+   > 3. portability — purge project-specific refs from shared package
+   > 4. seeder — scan seeders for broken FK references
+   > 5. pr — address all open review comments
+   > 6. pr-bots — address bot reviewer comments only
+   > 7. pr-developers — address human reviewer comments only
+
+## Rules
+
+- **Do NOT commit, push, or open a PR** unless the sub-command explicitly
+  authorizes it. Sub-command rules override these defaults only when stated.
+- **Do NOT chain sub-commands.** One `/fix <sub>` per turn.
+- If the user invokes `/fix` with no argument, **show the menu** — do not
+  guess which sub-command they meant.

package/.agent-src/commands/jira-ticket.md

@@ -72,4 +72,4 @@ suggestion:
 
 ## See also
 
-- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)
+- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)

package/.agent-src/commands/{do-and-judge.md → judge/on-diff.md}

@@ -1,6 +1,8 @@
 ---
-name: do-and-judge
-skills: [subagent-orchestration, verify-before-complete]
+name: judge:on-diff
+cluster: judge
+sub: on-diff
+skills: [subagent-orchestration, verify-completion-evidence]
 description: Run a single change through an implementer→judge loop with a two-revision ceiling, then hand back to the user
 disable-model-invocation: true
 suggestion:
@@ -8,8 +10,7 @@ suggestion:
   rationale: "Subagent orchestration — overlaps /work and judge skills; keep explicit."
 ---
 
-# do-and-judge
-
+# /judge on-diff
 ## Instructions
 
 ### 1. Confirm scope
@@ -90,7 +91,7 @@ Next step:  <commit / open PR / abandon>
 - No apply without the judge's `apply` verdict
 - No silent model fallback — unknown alias = stop and ask
 - No more than two revisions without user consent
-- No skipping of `verify-before-complete` on the final apply
+- No skipping of `verify-completion-evidence` on the final apply
 
 ## When to stop and ask
 
@@ -113,5 +114,5 @@ weaker verdicts.
 ## See also
 
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md)
-- [`verify-before-complete`](../skills/verify-before-complete/SKILL.md)
+- [`verify-completion-evidence`](../skills/verify-completion-evidence/SKILL.md)
 - [`subagent-configuration`](../contexts/subagent-configuration.md)