@event4u/agent-config 6.0.0 → 7.0.0

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: e2e-heal
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [playwright-testing]
 description: Find, debug, and fix failing Playwright E2E tests
 suggestion:

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: e2e-plan
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [playwright-testing]
 description: Explore the application and create a structured E2E test plan in Markdown
 suggestion:

package/dist/agent-src/commands/estimate-ticket.md

@@ -6,6 +6,7 @@ intent: "Estimate a tracker ticket's size, risk, and whether to split it"
 routes_to: [estimate-ticket]
 replaces: []
 tier: 1
+visibility: advanced
 skills: [estimate-ticket]
 description: Estimate a Jira/Linear ticket before sprint planning — size + risk + split recommendation + uncertainty, sibling to /refine-ticket, ends with a close-prompt
 suggestion:

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: feature-dev
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: feature
 sub: dev
 description: Full 7-phase feature development workflow for complex features.

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: feature-explore
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: feature
 sub: explore
 skills: [laravel]

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: feature-plan
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: feature
 sub: plan
 skills: [feature-planning]
@@ -113,12 +114,11 @@ Before asking detailed questions, **proactively research**:
   - Similar patterns already implemented
   - Database tables that would be affected
 - Read module-level `agents/` docs if a specific module is involved.
-- **Read `agents/memory/architecture-decisions.yml`** (if it exists) for active
-  ADRs whose `scope:` covers the affected modules. An ADR with
-  `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`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md).
+- **Read the ADR index `docs/decisions/INDEX.md`** for active ADRs whose
+  scope covers the affected modules. An ADR with `status: accepted` 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.
 
 **Share key findings with the user** — this informs the discussion:
 

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

@@ -3,6 +3,7 @@ model_tier: high
 name: feature-refactor
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: feature
 sub: refactor
 skills: [laravel, php-coder]

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: feature-roadmap
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: feature
 sub: roadmap
 skills: [agent-docs-writing]

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

@@ -7,6 +7,7 @@ intent: "Feature-workflow dispatcher — explore, plan, refactor, roadmap, dev"
 routes_to: [feature-explore, feature-plan, feature-refactor, feature-roadmap, feature-dev]
 replaces: []
 tier: 1
+visibility: advanced
 description: Feature orchestrator — routes to explore, plan, refactor, roadmap, dev
 cluster: feature
 type: orchestrator

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: fix-ci
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: fix
 sub: ci
 skills: [github-ci, quality-tools]

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: fix-portability
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: fix
 sub: portability
 skills: [check-refs]
@@ -22,7 +23,7 @@ packs:
 ### 1. Run the portability checker
 
 ```bash
-python3 src/scripts/check_portability.py --format json
+./scripts-run src/scripts/check_portability --format json
 ```
 
 ### 2. Parse findings
@@ -87,7 +88,7 @@ Edit files in `.agent-src.uncondensed/`, then run `bash src/scripts/condense.sh
 After all fixes, re-run:
 
 ```bash
-python3 src/scripts/check_portability.py
+./scripts-run src/scripts/check_portability
 ```
 
 ### 6. Mark hashes
@@ -95,7 +96,7 @@ python3 src/scripts/check_portability.py
 For each modified file:
 
 ```bash
-python3 src/scripts/condense.py --mark-done "{relative_path}"
+./scripts-run src/scripts/condense --mark-done "{relative_path}"
 ```
 
 ## Rules

package/dist/agent-src/commands/fix/pr-comments.md

@@ -3,9 +3,10 @@ model_tier: medium
 name: fix-pr-comments
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: fix
 sub: pr-comments
-skills: [php-coder]
+skills: [php-coder, quality-tools]
 description: Fix and reply to all open review comments (bots + human reviewers) on a GitHub PR
 suggestion:
   eligible: true
@@ -18,7 +19,12 @@ packs:
 ---
 
 # /fix pr-comments
-This command runs `/fix pr-bot-comments` and `/fix pr-developer-comments` in sequence on the same PR.
+
+Single surface for addressing all open PR review comments — **bot**
+(Copilot, Greptile, Augment, …) and **human reviewers** — in one pass.
+Each unresolved comment is classified by author type and handled with the
+right detection and reply style. Dedupes by comment id + reply marker;
+never replies twice.
 
 ## Input
 
@@ -38,32 +44,158 @@ The user may or may not provide a PR URL.
 
 ## Mode selection
 
-After the PR is confirmed, ask the user:
+After the PR is confirmed, ask the user (use numbered options per `user-interaction` rule):
 
 ```
 > 1. Interactive — ask before each comment
 > 2. Automatic — handle all independently
 ```
 
-The chosen mode applies to **both** phases.
+- **Option 1** → follow the "Interactive flow" below.
+- **Option 2** → follow the "Auto flow" below.
+
+The chosen mode applies to **every** comment, bot and human alike.
+
+## Comment classification
+
+- A comment is from a **bot** if the GitHub user has `type: "Bot"` or the
+  login matches a known bot account: `Copilot`, `github-actions[bot]`,
+  `greptile[bot]`, `augment[bot]`, or any login ending in `[bot]`.
+- A comment is from a **human reviewer** if the user `type` is `"User"`, the
+  login does NOT end in `[bot]`, and the user is NOT the PR author (never
+  process your own comments).
+
+## Instructions (shared)
+
+1. **Fetch all review comments** from the PR using the GitHub API
+   (`/pulls/{number}/comments`, `per_page: 100`). Also fetch **PR reviews**
+   (`/pulls/{number}/reviews`) for top-level human review comments. Filter for
+   comments that have **no reply yet** from the PR author.
+2. **Classify** each unresolved comment as bot or human (rules above).
+3. **For each comment**, read the affected file and surrounding context to
+   understand the code and the suggestion / request.
+4. **Report the totals** to the user: "Found X unresolved bot comments and Y
+   unresolved reviewer comments."
+
+---
+
+## Interactive flow
+
+For each comment, present it to the user **before** taking action.
+
+### 1. Summarize the comment
+
+In the **user's language**, briefly explain:
+- Whether it's a bot or a named human reviewer (login)
+- Which file/line is affected
+- What is being suggested / requested
+- Your assessment: valid, partially valid, a question, a style preference, or not applicable
+
+### 2. Offer options
+
+Present numbered options. Always include a "leave as-is" / "skip" option.
+
+**Bot — one clear fix:**
+> **Comment 1/3** — `WorkingTimeService.php:108`
+> Bot says: The guard condition only checks `job_start`, but the comment also mentions `job_stop`.
+>
+> 1. Fix the comment (only mention `job_start`)
+> 2. Extend the guard condition (also check `job_stop`)
+> 3. Leave as-is, dismiss comment
+
+**Bot — multiple valid approaches:**
+> **Comment 2/3** — `AbsencePlannerService.php:520`
+> Bot says: When an exception occurs mid-loop, log entries are missing.
+>
+> 1. `writeLogBulk()` in einen `finally`-Block verschieben
+> 2. Die gesamte Schleife in eine DB-Transaction wrappen
+> 3. Leave as-is, dismiss comment
+
+**Human — change request:**
+> **Comment 1/3** — @cjost1988 in `WorkingTimeService.php:108`
+> Reviewer asks: Why is the fallback `float`? `$time` is `$hours * 60`.
+>
+> 1. Reply and explain why (no code change needed)
+> 2. Adjust type annotation to `float|int|string`
+> 3. Skip
+
+**Human — question (no code change needed):**
+> **Comment 3/3** — @cjost1988 in `KS21Client.php:42`
+> Reviewer asks: Is this fallback ever reached?
+>
+> 1. Reply with explanation
+> 2. Skip
+
+### 3. Wait for the user's choice
+
+- Do NOT proceed until the user picks an option.
+- If the user wants a custom reply, let them dictate the text.
+- If the user asks a follow-up question, answer it before proceeding.
+- After the user chooses, apply the fix (or skip) and reply on GitHub.
+
+### 4. Move to the next comment
+
+Repeat until all comments are handled.
+
+---
+
+## Auto flow
+
+Process all comments without asking. For each comment:
+
+**Bot comments:**
+1. Analyze whether the suggestion is valid.
+2. **If valid** — fix it and reply on GitHub.
+3. **If not valid** — reply on GitHub explaining why, do NOT change the code.
+
+**Human reviewer comments:**
+1. **Clear code fix** — fix it and reply on GitHub.
+2. **Question** — reply with a concise explanation on GitHub.
+3. **Ambiguous or a design decision** — do NOT guess; collect these and present
+   them at the end: "These comments need your decision: …".
+
+---
+
+## Common bot patterns to watch for
+
+- **Duplicate PHPDoc tags** → fix by keeping the more specific/typed version.
+- **Split PHPDoc blocks** → merge into a single docblock.
+- **Wrong PHPDoc tag order** → `@param` before `@return` before `@throws`.
+- **Conflicting PHPDoc types** → remove incorrect PHPDoc, trust the method signature.
+- **Broad ignore patterns / intentional config** → reply explaining rationale, don't change.
+- **Validation/logic bugs** → fix the code.
+
+## Reply style — write like a human developer, not an AI
+
+- The GitHub API token authenticates as the PR author. Write replies as if you ARE the developer.
+- Keep it casual, short, and natural. Like a real dev replying to a code review.
+- Vary your wording — never use the same opening phrase twice in a row.
+- Don't over-explain. A dev who fixed something doesn't write a paragraph about it.
+- For reviewer questions: answer directly and concisely.
+- Be respectful — human reviewers are colleagues, not bots. Don't dismiss feedback.
+- Good examples: `"Good catch, fixed."`, `"Yep, consolidated into one docblock now."`,
+  `"Removed the duplicate 👍"`, `"That's intentional — [reason]"`,
+  `"The fallback covers legacy data where getTime() returns a string."`
+- Never start multiple replies with "Fixed". Mix it up: "Done", "Good catch", "Yep", etc.
 
-## Execution
+### Bot icon prefix
 
-### Phase 1: Bot comments
+Read `personal.pr_comment_bot_icon` from `.agent-settings.yml`. If `true` (default),
+prefix every reply with `🤖 ` so reviewers can see at a glance that the reply was
+bot-authored.
 
-Follow the full `/fix pr-bot-comments` instructions (see `commands/fix/pr-bot-comments.md`).
-Use the already-confirmed PR and mode — do not ask again.
+Example: `🤖 Good catch, fixed.`
 
-Report when done: "Bot comments done. Continuing with reviewer comments..."
+If `false` or `.agent-settings.yml` doesn't exist, do NOT add the prefix.
 
-### Phase 2: Developer comments
+## Replying via GitHub API
 
-Follow the full `/fix pr-developer-comments` instructions (see `commands/fix/pr-developer-comments.md`).
-Use the same PR and mode.
+Read `github.pr_reply_method` from `.agent-settings.yml` to determine the correct endpoint.
+See the `command-routing` skill → "GitHub API: Replying to PR review comments" for full details.
 
-### After both phases
+## After all comments
 
 1. Run a PHP syntax check (`php -l`) on all modified files to verify nothing is broken.
-2. Report a final summary: how many bot comments handled, how many developer comments handled,
-   how many files modified.
+2. Report a final summary: how many bot comments handled, how many reviewer
+   comments handled, how many files modified.
 3. **Do NOT commit or push.** Just apply the fixes locally and reply to all comments on GitHub.

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: fix-refs
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: fix
 sub: refs
 skills: [check-refs]
@@ -22,7 +23,7 @@ packs:
 ### 1. Run the reference checker
 
 ```bash
-python3 src/scripts/check_references.py --format json
+./scripts-run src/scripts/check_references --format json
 ```
 
 ### 2. Parse findings
@@ -82,7 +83,7 @@ Edit files in `.agent-src.uncondensed/` (source of truth). Regenerate `dist/agen
 After all fixes:
 
 ```bash
-python3 src/scripts/check_references.py
+./scripts-run src/scripts/check_references
 ```
 
 Show final result.
@@ -92,7 +93,7 @@ Show final result.
 For each modified file:
 
 ```bash
-python3 src/scripts/condense.py --mark-done "{relative_path}"
+./scripts-run src/scripts/condense --mark-done "{relative_path}"
 ```
 
 ## Rules

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: fix-seeder
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: fix
 sub: seeder
 skills: [eloquent]

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

@@ -7,7 +7,8 @@ intent: "Fix-workflow dispatcher — ci, pr-comments, refs, seeder, portability"
 routes_to: [fix-ci, fix-pr-comments, fix-refs, fix-seeder, fix-portability]
 replaces: []
 tier: 1
-description: Fix orchestrator — routes to ci, references, portability, seeder, pr-comments, pr-bot-comments, pr-developer-comments
+visibility: advanced
+description: Fix orchestrator — routes to ci, references, portability, seeder, pr-comments
 cluster: fix
 type: orchestrator
 auto_detect: true
@@ -34,9 +35,7 @@ with a single entry point + sub-command dispatch.
 | `/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-comments` | `commands/fix/pr-comments.md` | Fix and reply to open review comments — **detects bot / human / both** and asks which when ambiguous; dedupes by comment id + reply marker |
-| `/fix pr-bot-comments` | `commands/fix/pr-bot-comments.md` | **Deprecated → `fix pr-comments`** (the "bots" answer to its prompt) |
-| `/fix pr-developer-comments` | `commands/fix/pr-developer-comments.md` | **Deprecated → `fix pr-comments`** (the "human" answer to its prompt) |
+| `/fix pr-comments` | `commands/fix/pr-comments.md` | Fix and reply to all open review comments — **bot + human, classified per comment**; dedupes by comment id + reply marker |
 
 Sub-command names match the locked contract in
 [`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
@@ -57,10 +56,11 @@ the `auto_detect` kill-switch, rollback). Detection table:
 | Project-specific leakage in shared package named | `fix/portability` | MEDIUM |
 | No clear signal, or ≥ 2 conflict | — | LOW → menu (interactive) / `ambiguous_routing` (CI) |
 
-`fix/pr-comments` is the single PR-review-comment surface: it absorbs the
-deprecated bot- and developer-only variants by detecting unanswered
-comments and asking "fix bot / human / both?" (deduped by id + reply
-marker). Auto-detection never routes to the deprecated variants.
+`fix/pr-comments` is the single PR-review-comment surface: it handles bot
+and human comments in one pass — classifying each unanswered comment by
+author type and applying the right detection + reply style (deduped by id +
+reply marker). The former bot-only and developer-only variants were folded
+into it and removed.
 
 ## Dispatch
 

package/dist/agent-src/commands/ghostwriter/delete.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter-delete
 pack: gtm-marketing
 tier: 2
+visibility: internal
 cluster: ghostwriter
 sub: delete
 skills: [ghostwriter]

package/dist/agent-src/commands/ghostwriter/fetch.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter-fetch
 pack: gtm-marketing
 tier: 2
+visibility: internal
 cluster: ghostwriter
 sub: fetch
 description: Build or refresh a public-figure voice profile under agents/reference/ghostwriter/ from a URL or bare name; runs the public-figure attestation gate; delegates web-fetch/web-search to host.

package/dist/agent-src/commands/ghostwriter/list.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter-list
 pack: gtm-marketing
 tier: 2
+visibility: internal
 cluster: ghostwriter
 sub: list
 skills: [ghostwriter]

package/dist/agent-src/commands/ghostwriter/show.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter-show
 pack: gtm-marketing
 tier: 2
+visibility: internal
 cluster: ghostwriter
 sub: show
 skills: [ghostwriter]

package/dist/agent-src/commands/ghostwriter/write.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter-write
 pack: gtm-marketing
 tier: 2
+visibility: internal
 cluster: ghostwriter
 sub: write
 description: Draft a markdown post in the voice of a captured public-figure ghostwriter profile; appends the mandatory non-removable disclosure footer.

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: ghostwriter
 pack: gtm-marketing
 tier: 2
+visibility: internal
 description: Ghostwriter cluster — fetch, write, list, show, and delete public-figure voice profiles (the third voice primitive alongside personas/ and .agent-user.md).
 cluster: ghostwriter
 type: orchestrator

package/dist/agent-src/commands/grill-me.md

@@ -1,8 +1,9 @@
 ---
 model_tier: inherit
 name: grill-me
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 description: Alias for /challenge-me — interactive grill-style interview that sharpens a fuzzy plan/idea into a copyable Markdown pitch
 cluster: challenge-me
 type: orchestrator
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /grill-me

package/dist/agent-src/commands/image/analyse.md

@@ -3,6 +3,7 @@ model_tier: high
 name: image-analyse
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: image
 sub: analyse
 description: Analyse a character image down to the smallest mole and diff it against a canon — per-feature spec, OCR tattoo text, severity-ranked drift report.

package/dist/agent-src/commands/image/create.md

@@ -3,6 +3,7 @@ model_tier: high
 name: image-create
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: image
 sub: create
 description: Generate a character image to spec — assemble a max-fidelity, anchors-first prompt from a Canon Spec; governance- and provider-gated, dry-run by default.

package/dist/agent-src/commands/image/verify.md

@@ -3,6 +3,7 @@ model_tier: high
 name: image-verify
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: image
 sub: verify
 description: Verify a candidate render against its canon — run the analyser in loop mode, emit the gate verdict + remaining diff, halt-and-surface on non-pass.

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: image
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: image
 description: Character-image fidelity orchestrator — analyse, create, and verify a character image against its canon. Routes to analyse, create, verify.
 type: orchestrator

package/dist/agent-src/commands/implement-ticket.md

@@ -6,6 +6,7 @@ intent: "Implement a tracker ticket end-to-end from its id"
 routes_to: [refine-ticket, feature-planning]
 replaces: []
 tier: 0
+visibility: visible
 skills: [refine-ticket, feature-planning]
 description: Drive a ticket end-to-end through refine → memory → analyze → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, block-on-ambiguity, no auto-git.
 suggestion:
@@ -24,22 +25,51 @@ packs:
 
 ### 1. Resolve input
 
-Accept one of four input paths:
+Accept one of five input paths:
 
 1. **Explicit key** — `/implement-ticket PROJ-123`
 2. **Branch detection** — no arg → `git branch --show-current` + regex
    `[A-Z]+-[0-9]+`
 3. **Pasted text** — markdown block under the command
 4. **URL** — `/implement-ticket https://…/browse/PROJ-123`
+5. **Local ticket bundle** — a path to a bundle ticket file,
+   `/implement-ticket agents/tickets/{slug}/T-NNN-….md` (the
+   ticket-bundle artifact from [`emit-tickets`](emit-tickets.md);
+   format: [`ticket-bundle-format`](../docs/contracts/ticket-bundle-format.md)).
 
 For paths 1, 2, 4: run steps 1-3 of the [`jira-ticket`](jira-ticket.md) command
 (extract ID, fetch ticket, scan for Sentry links). For path 3: parse the pasted
-markdown. If no input resolves:
+markdown. For path 5: parse the bundle ticket — its YAML frontmatter +
+Markdown body map straight onto the work-state envelope with **no engine
+schema fork** (`input.data = {id, title, body, acceptance_criteria}`; the
+ticket `acceptance` list → `acceptance_criteria`, the body → `body`). Then
+apply the **bundle-mode guards** in §1a before driving the engine. If no
+input resolves:
 
 ```
 🎫 Which ticket should I implement? Paste a key, URL, or the ticket text.
 ```
 
+### 1a. Bundle-mode guards (path 5 only)
+
+When the input is a local ticket bundle, three guards run **before** the
+engine — they make a `lite`-tier build safe (per
+[`ADR-101`](../../docs/decisions/ADR-101-ticket-bundle-emission.md)):
+
+- **Dependency-driven selection.** Read the bundle `manifest.yml`
+  `dependency_graph`. Only build a ticket whose `blocked_by` are all
+  `done`. If a dependency is open, STOP and surface it — never build
+  out of order.
+- **Pre-build staleness gate.** Run
+  `python3 src/scripts/lint_ticket_buildable.ts` on the bundle. An
+  `adr_refs` SHA drift is a **hard** stop ("re-emit the bundle"); a
+  `source_refs` SHA drift only **warns** and proceeds (split severity).
+- **Boundary guard.** Carry the ticket's `boundaries`
+  (`must_touch` / `may_touch` / `must_not_touch`) into the
+  `apply-plan` and `review-changes` directives (§4). Any changeset file
+  outside `must_touch ∪ may_touch` HALTS with an escalation surface —
+  prose "do not touch" does not bind a cheap agent; this guard does.
+
 ### 2. Prepare the state file
 
 The engine persists everything in a JSON state file (default:
@@ -58,10 +88,11 @@ Three cases, in this order:
   ./agent-config migrate
   ```
 
-  Unified `migrate` writes `.work-state.json`, renames source to
-  `.implement-ticket-state.json.bak`, sweeps other legacy install
-  artefacts (see `docs/contracts/migrate-command.md`). Idempotent and
-  safe to skip if already done. After this, treat the run as **Resume**.
+  The unified `migrate` command writes `.work-state.json`, renames the
+  source to `.implement-ticket-state.json.bak`, and sweeps any other
+  legacy install artefacts in the same pass (see
+  `docs/contracts/migrate-command.md`). Idempotent and safe to skip if
+  already done. After this, treat the run as **Resume**.
 - **Fresh run** — no state file at all. Write the resolved ticket to
   `ticket.json` (id, title, body, acceptance_criteria) and pass it via
   `--ticket-file ticket.json`. Honour `roles.active_role` from

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

@@ -6,6 +6,7 @@ intent: "Read a Jira ticket from the branch and implement the feature or fix the
 routes_to: [jira-integration, feature-planning]
 replaces: []
 tier: 1
+visibility: advanced
 skills: [laravel]
 description: Read Jira ticket from branch name, analyze linked Sentry issues, implement feature or fix bug
 suggestion:

package/dist/agent-src/commands/judge/on-diff.md

@@ -3,6 +3,7 @@ model_tier: high
 name: judge-on-diff
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: judge
 sub: on-diff
 skills: [subagent-orchestration, verify-completion-evidence]

package/dist/agent-src/commands/judge/solo.md

@@ -3,6 +3,7 @@ model_tier: high
 name: judge-solo
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: judge
 sub: solo
 skills: [subagent-orchestration]

package/dist/agent-src/commands/judge/steps.md

@@ -3,6 +3,7 @@ model_tier: high
 name: judge-steps
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: judge
 sub: steps
 skills: [subagent-orchestration, verify-completion-evidence]

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

@@ -7,6 +7,7 @@ intent: "Adversarial-judging dispatcher — solo, on-diff, steps"
 routes_to: [judge-solo, judge-on-diff, judge-steps]
 replaces: []
 tier: 1
+visibility: advanced
 description: Judge orchestrator — routes to solo, steps, on-diff
 cluster: judge
 type: orchestrator