@event4u/agent-config 8.13.0 → 9.0.0

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

@@ -5,6 +5,7 @@ pack: meta
 tier: 2
 visibility: internal
 description: Session-profile orchestrator — activate / deactivate / show the active packs for this session (recommendation-bias surface filter, no persistence)
+argument-hint: "[activate|deactivate|show] [args]"
 cluster: profile
 type: orchestrator
 suggestion:

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

@@ -2,6 +2,7 @@
 model_tier: medium
 name: project
 disable-model-invocation: true
+argument-hint: "[analyze|health]"
 pack: engineering-base
 intent: "Project dispatcher — full analysis or quick health check"
 routes_to: [project-analyze, project-health]
@@ -37,7 +38,7 @@ Top-level orchestrator for the `/project` family — project-wide inspection.
 | `/project health` | `commands/project/health.md` | Quick health check — status of docs, modules, contexts, roadmaps; creates nothing |
 
 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).
 
 ## Dispatch
 

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

@@ -9,6 +9,7 @@ tier: 1
 visibility: advanced
 skills: [refine-ticket]
 description: Refine a Jira/Linear ticket before planning — rewritten ticket + Top-5 risks + persona voices, orchestrates validate-feature-fit and threat-modeling, ends with a close-prompt
+argument-hint: "[ticket-key | url | text] [--personas=<list>] [--user-type=<id>] [--fresh-eyes]"
 suggestion:
   eligible: true
   trigger_description: "refine PROJ-123, tighten the acceptance criteria, is this ticket clear"
@@ -68,6 +69,12 @@ application, synthesis, and close-prompt.
 - `--personas=<list>` — comma-separated override of the Core-6 default
   (e.g. `--personas=developer,senior-engineer,critical-challenger`)
 - `--personas=+qa` — add the QA specialist to the Core-6
+- `--user-type=<id>` — load one user-type from `user-types/<id>.md` and
+  add an end-user simulation lens to the persona stack (e.g.
+  `--user-type=galabau-field-crew`). Composes orthogonally with
+  `--personas=`; persona = methodology lens, user-type = end-user lens.
+  v1 is CLI-only (no skill-level default). Contract:
+  [`docs/contracts/user-type-schema.md`](../docs/contracts/user-type-schema.md).
 - `--fresh-eyes` — reweight toward first-time-reader confusion signals
   (critical-challenger voice gets more lines; less assumed context)
 

package/dist/agent-src/commands/research/deep.md

@@ -7,6 +7,7 @@ visibility: internal
 cluster: research
 sub: deep
 description: "Read `outline.yaml`, research each item in batches, write per-item JSON validated against the project-local research-schema. No Python runtime, no `~/.claude/` paths."
+argument-hint: "[--batch-confirm=each|once|auto]"
 skills: [deep-reading-analyst]
 suggestion:
   eligible: true

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

@@ -2,6 +2,7 @@
 model_tier: high
 name: research
 disable-model-invocation: true
+argument-hint: "[<topic>|deep|report] [args]"
 pack: product-discovery
 tier: 2
 visibility: internal

package/dist/agent-src/commands/review/routing.md

@@ -8,6 +8,7 @@ sub: routing
 cluster: review
 skills: [review-routing, reviewer-awareness]
 description: Compute reviewer roles and matched historical bug patterns for the current diff, using project-local ownership-map.yml and historical-bug-patterns.yml
+argument-hint: "[base-ref head-ref]"
 suggestion:
   eligible: true
   trigger_description: "who should review this, suggest reviewers for this PR"

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

@@ -2,6 +2,7 @@
 model_tier: medium
 name: review
 disable-model-invocation: true
+argument-hint: "[changes|routing]"
 pack: engineering-base
 intent: "Review dispatcher — multi-judge self-review of the current diff, or reviewer routing"
 routes_to: [review-changes, review-routing]
@@ -38,7 +39,7 @@ reviewer selection.
 | `/review routing` | `commands/review/routing.md` | Compute reviewer roles + matched historical bug patterns for the current diff (ownership-map.yml, historical-bug-patterns.yml) |
 
 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).
 
 ## Dispatch
 

package/dist/agent-src/commands/roadmap/ai-council.md

@@ -8,6 +8,7 @@ cluster: roadmap
 sub: ai-council
 skills: [ai-council, agent-docs-writing, roadmap-management]
 description: Challenge a roadmap with the AI council (deep tier) and refactor from convergence findings. Wraps `/council default` pinned to `--input-mode roadmap --depth deep`; patches surface as numbered options.
+argument-hint: "[roadmap-name | path]"
 council_depth: deep
 suggestion:
   eligible: true

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

@@ -8,6 +8,7 @@ cluster: roadmap
 sub: materialize
 skills: [emit-tickets]
 description: Materialise a roadmap into a self-contained, importable ticket bundle under agents/tickets/
+argument-hint: "[roadmap-path]"
 suggestion:
   eligible: true
   trigger_description: "turn this roadmap into tickets, materialise the roadmap, mach Tickets aus der Roadmap"

package/dist/agent-src/commands/roadmap/process-full.md

@@ -8,6 +8,7 @@ cluster: roadmap
 sub: process-full
 skills: [agent-docs-writing, ai-council, roadmap-management]
 description: Autonomously process every open step across every phase of a roadmap until the file is fully closed. Largest execution scope of the /roadmap cluster — runs continuously across phase boundaries.
+argument-hint: "[roadmap]"
 suggestion:
   eligible: true
   trigger_description: "process the whole roadmap, finish the roadmap, komplette roadmap abarbeiten"

package/dist/agent-src/commands/roadmap/process-phase.md

@@ -8,6 +8,7 @@ cluster: roadmap
 sub: process-phase
 skills: [agent-docs-writing, ai-council, roadmap-management]
 description: Autonomously process every open step in the next or current phase of a roadmap, then stop. Default execution scope of the /roadmap cluster.
+argument-hint: "[roadmap]"
 suggestion:
   eligible: true
   trigger_description: "process the next phase, finish this phase autonomously, eine phase abarbeiten"

package/dist/agent-src/commands/roadmap/process-step.md

@@ -8,6 +8,7 @@ cluster: roadmap
 sub: process-step
 skills: [agent-docs-writing, ai-council, roadmap-management]
 description: Autonomously process the single next open step of a roadmap and stop. Smallest execution scope of the /roadmap cluster — one step in, one step out.
+argument-hint: "[roadmap]"
 suggestion:
   eligible: true
   trigger_description: "process the next step, do the next roadmap step, einen schritt abarbeiten"

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

@@ -2,6 +2,7 @@
 model_tier: medium
 name: roadmap
 disable-model-invocation: true
+argument-hint: "[create|ai-council|process-step|process-phase|process-full] [args]"
 pack: product-basic
 intent: "Roadmap dispatcher — create, process-step, process-phase, process-full, ai-council"
 routes_to: [roadmap-create, roadmap-process-step, roadmap-process-phase, roadmap-process-full]

package/dist/agent-src/commands/security-audit-config.md

@@ -6,6 +6,7 @@ tier: 2
 visibility: internal
 skills: [judge-security-auditor, threat-modeling, security-audit]
 description: Audit an assembled agent config (CLAUDE.md, .cursor/rules, settings, MCP, hooks, skills) for prompt-injection / supply-chain risk — A–F score per category, mapped to OWASP Agentic Top 10
+argument-hint: "[repo-root]"
 council_depth: deep
 suggestion:
   eligible: true
@@ -35,7 +36,7 @@ suite's own `lint_agent_security` self-audit gate.
 
 (omit `--root` to audit the current repo). The script reuses the Phase-1
 detection library under the false-positive containment convention
-([`security-lint-containment`](../../../docs/guidelines/agent-infra/security-lint-containment.md)),
+([`security-lint-containment`](../../docs/guidelines/agent-infra/security-lint-containment.md)),
 so doc/example files do not tank the score. It scans instruction files
 (`CLAUDE.md`, `AGENTS.md`, `.cursor/rules`, `.github/copilot-instructions.md`,
 `.clinerules`, `.windsurfrules`), MCP configs (`.mcp.json`, `.cursor/mcp.json`,

package/dist/agent-src/commands/skill/preview.md

@@ -7,6 +7,7 @@ visibility: internal
 cluster: skill
 sub: preview
 description: Non-destructive preview of a skill — its declared steps, execution type, allowed tools, and file/command targets — before you run it. Read-only, no execution.
+argument-hint: "<skill-name> [--technical]"
 skills: [file-editor]
 suggestion:
   eligible: true

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

@@ -5,6 +5,7 @@ pack: meta
 tier: 2
 visibility: internal
 description: Single-skill orchestrator — routes to preview. Non-destructive "what will this skill do?" before you run it.
+argument-hint: "[preview] <skill-name>"
 cluster: skill
 type: orchestrator
 suggestion:

package/dist/agent-src/commands/skills/discover.md

@@ -7,6 +7,7 @@ visibility: internal
 cluster: skills
 sub: discover
 description: Recommend skills for a role — ranked by four explained classes (most-useful-for-role, related-to-current-task, recently-adopted, popular-in-role). Local-only; every result carries a why.
+argument-hint: "[role]"
 skills: [file-editor]
 suggestion:
   eligible: true

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

@@ -5,6 +5,7 @@ pack: meta
 tier: 2
 visibility: internal
 description: Skill discovery orchestrator — routes to discover. Local, explained skill recommendations over the catalog + role shortlists + optional local analytics.
+argument-hint: "[discover] [role]"
 cluster: skills
 type: orchestrator
 suggestion:

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

@@ -8,6 +8,7 @@ sub: agent-settings
 cluster: sync
 skills: [sync-agent-settings]
 description: Sync `.agent-settings.yml` against the current template + profile — adds new sections/keys, preserves user values, shows a diff before writing
+argument-hint: "[--path <file>] [--profile minimal|balanced|full] [--check]"
 suggestion:
   eligible: false
   rationale: "Settings sync — must be deliberate."

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

@@ -2,6 +2,7 @@
 model_tier: medium
 name: sync
 disable-model-invocation: true
+argument-hint: "[agent-settings|gitignore|gitignore-fix]"
 pack: meta
 intent: "Sync dispatcher — agent settings or the managed .gitignore block"
 routes_to: [sync-agent-settings, sync-gitignore, sync-gitignore-fix]
@@ -34,7 +35,7 @@ managed files in step with the package templates.
 | `/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).
+[`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
 
 ## Dispatch
 

package/dist/agent-src/commands/team/adversarial.md

@@ -2,7 +2,8 @@
 model_tier: inherit
 name: team-adversarial
 disable-model-invocation: true
-pack: product-reasoning
+argument-hint: "<focus>"
+pack: meta
 tier: 2
 visibility: internal
 skills: [adversarial-review]
@@ -16,7 +17,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - product-reasoning
+  - meta
 ---
 
 # /team adversarial

package/dist/agent-src/commands/team/delegate.md

@@ -2,7 +2,8 @@
 model_tier: inherit
 name: team-delegate
 disable-model-invocation: true
-pack: product-reasoning
+argument-hint: "<task>"
+pack: meta
 tier: 2
 visibility: internal
 description: Thin wrapper — hand a task to the second model as a native worker via the official plugin (/codex:rescue). The only write-access wrapper; double-gated behind ai_team.allow_delegate.
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - product-reasoning
+  - meta
 ---
 
 # /team delegate

package/dist/agent-src/commands/team/review.md

@@ -2,7 +2,8 @@
 model_tier: inherit
 name: team-review
 disable-model-invocation: true
-pack: product-reasoning
+argument-hint: "[--background]"
+pack: meta
 tier: 2
 visibility: internal
 description: Thin wrapper — cross-model review of the current diff via the official plugin (/codex:review). Gated on ai_team.enabled; fails closed when the plugin is absent.
@@ -15,7 +16,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - product-reasoning
+  - meta
 ---
 
 # /team review

package/dist/agent-src/commands/team/status.md

@@ -2,10 +2,10 @@
 model_tier: inherit
 name: team-status
 disable-model-invocation: true
-pack: product-reasoning
+pack: meta
 tier: 2
 visibility: internal
-description: Thin wrapper — plugin job status via /codex:status plus a ledger line with today's cli_call_budget openai count. Gated on ai_team.enabled; fails closed when the plugin is absent.
+description: Thin wrapper — plugin job status via /codex:status plus a quota block (shared openai counter vs team + council ceilings). Gated on ai_team.enabled; fails closed without the plugin.
 cluster: team
 sub: status
 suggestion:
@@ -14,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - product-reasoning
+  - meta
 ---
 
 # /team status
@@ -22,7 +22,7 @@ packs:
 ## Instructions
 
 Thin wrapper: team-mode status. On Claude Code hosts it delegates to the
-official plugin's `/codex:status` and appends **our** quota ledger line —
+official plugin's `/codex:status` and appends **our** quota block —
 the one piece of state the plugin does not know about.
 
 ### 1. Gate — `ai_team.enabled`
@@ -38,7 +38,7 @@ print the fail-closed block from `/team` (master) § "Fail-closed contract"
 (`agent-config doctor --check team`) and **STOP** — never a silent no-op.
 
 On a non-Claude-Code host: state that plugin job status requires the Claude
-Code plugin, then still print the ledger line (Step 4) — the quota counter
+Code plugin, then still print the quota block (Step 4) — the quota counter
 is ours and host-independent.
 
 ### 3. Delegate
@@ -49,28 +49,59 @@ Invoke the plugin:
 
 Render its job/status output verbatim.
 
-### 4. Append the quota ledger line
+### 4. Append the quota block — two ceilings, one counter
 
-Read today's openai CLI-call count from the shared counter state at
-`~/.event4u/agent-config/cli-calls.json` (daily UTC reset — the same file
-the council's CLI transport maintains for
-`cli_call_budget.max_calls_per_day.openai`). Append one line:
+Team mode and the council share **one** daily counter but enforce **two
+independent ceilings** against it. The status output must show all three
+live numbers and say which path — if any — is currently blocked:
+
+1. **Counter** — today's openai CLI-call count from the shared counter
+   state at `~/.event4u/agent-config/cli-calls.json` (daily UTC reset —
+   the same file the council's CLI transport maintains). `0` when the
+   file or today's entry is absent.
+2. **Team ceiling** — `ai_team.max_calls_per_day` from
+   `.agent-settings.yml` (`unset` when absent).
+3. **Council ceiling** — `cli_call_budget.max_calls_per_day.openai` from
+   the council config (`unset` when absent).
+
+Render:
 
 ```
-Ledger: <N> openai CLI calls today (UTC) · cap: <max_calls_per_day or "unset">
+Quota: <N> openai CLI calls today (UTC) — one shared counter
+  team ceiling (ai_team.max_calls_per_day):                <T or "unset"> → <OPEN | BLOCKED>
+  council ceiling (cli_call_budget.max_calls_per_day.openai): <C or "unset"> → <OPEN | BLOCKED>
 ```
 
-- `<N>` = today's openai count from the counter file; `0` when the file or
-  today's entry is absent.
-- `<cap>` = `ai_team.max_calls_per_day` when set; fall back to
-  `cli_call_budget.max_calls_per_day.openai`; `unset` when neither exists.
+- A path is `BLOCKED` when the counter has reached its ceiling
+  (`N >= ceiling`); an `unset` ceiling is `OPEN`.
+- The two paths block **independently** — always name WHICH path is
+  blocked, never a bare "quota exhausted".
 - One counter, one subscription — never introduce a parallel team-only
   counting file.
 
+**Worked example.** Council ceiling 100, team ceiling 50, counter at 45:
+both paths are open. Five team calls later the shared counter reads 50 —
+team calls are now `BLOCKED` (50 >= 50) while council CLI calls continue
+until the counter reaches 100. Whichever path fires a call, the same
+counter moves; each surface only enforces its own ceiling against that
+shared count.
+
+### 5. Review-gate ledger lines (when present)
+
+When the council events ledger contains review-gate lines of the form
+`team.gate: BLOCK n/N`, render them verbatim after the quota block — they
+record how often the plugin's Stop-hook Review Gate blocked, out of N gate
+evaluations. Absent lines are not an error: print nothing (the review-gate
+envelope is a later team-mode phase; this step is read-only forward
+compatibility).
+
 ## Output format
 
 - The plugin's status output, verbatim.
-- Exactly one trailing `Ledger:` line in the format above.
+- Exactly one trailing `Quota:` block in the format above (counter + both
+  ceilings + per-path OPEN/BLOCKED verdict).
+- Any `team.gate: BLOCK n/N` ledger lines, verbatim, after the quota
+  block — only when present.
 - Gate failures print exactly one block (enable pointer or fail-closed
   block) and stop.
 
@@ -78,11 +109,11 @@ Ledger: <N> openai CLI calls today (UTC) · cap: <max_calls_per_day or "unset">
 
 - Do NOT run when `ai_team.enabled` is false — enable pointer, stop.
 - Do NOT fabricate a count when the counter file is unreadable — print
-  `Ledger: unavailable (<reason>)` instead of a guessed number.
+  `Quota: unavailable (<reason>)` instead of a guessed number.
 - Do NOT write to `cli-calls.json` — the transport owns the counter; this
   wrapper is read-only.
 - Do NOT reimplement job tracking inline when the plugin is absent — fail
-  closed with the doctor pointer (the ledger line alone is still printed on
+  closed with the doctor pointer (the quota block alone is still printed on
   non-Claude-Code hosts, per Step 2).
 
 ## See also

package/dist/agent-src/commands/team-knowledge.md

@@ -2,6 +2,7 @@
 model_tier: medium
 name: team-knowledge
 disable-model-invocation: true
+argument-hint: "[consolidate|bootstrap]"
 pack: meta
 intent: "Manage the repo-tracked team-knowledge layer — consolidate typed observation events into agents/knowledge/ pages, bootstrap a project baseline"
 routes_to: [team-knowledge-consolidate, team-knowledge-bootstrap]
@@ -26,13 +27,14 @@ packs:
 Top-level orchestrator for the `/team-knowledge` family — the
 consolidation gate over the typed knowledge-observation events
 captured during normal task work (see
-[`knowledge-pages`](../templates/contexts/knowledge-pages.md) and the
-event schema in `src/scripts/_lib/knowledge_events.ts`).
+[`knowledge-pages`](../../agent-src/templates/contexts/knowledge-pages.md)
+and the event schema in `src/scripts/_lib/knowledge_events.ts`).
 
-Not to be confused with the pre-existing `/knowledge` cluster (local
-file ingestion into `agents/memory/knowledge/`) — different concern
-(arbitrary local documents), unrelated to this repo-tracked,
-lifecycle-typed team-knowledge layer under `agents/knowledge/`.
+Not to be confused with the pre-existing [`/knowledge`](../../product-discovery/knowledge/command.md)
+cluster (local file ingestion into `agents/memory/knowledge/`) — that
+is a different concern (arbitrary local documents), unrelated to this
+repo-tracked, lifecycle-typed team-knowledge layer under
+`agents/knowledge/`.
 
 ## Sub-commands
 

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

@@ -2,13 +2,14 @@
 model_tier: inherit
 name: team
 disable-model-invocation: true
-pack: product-reasoning
+argument-hint: "[review|adversarial|delegate|status] [args]"
+pack: meta
 intent: "Route a cross-model team-mode request (review, adversarial, delegate, status) to the official plugin under ai_team governance"
 routes_to: [team-review, team-adversarial, team-delegate, team-status]
 replaces: []
 tier: 2
 visibility: internal
-description: Team orchestrator — cross-model depth review (one strong model builds, a second reviews the real diff); routes to review, adversarial, delegate, status
+description: Team orchestrator — governed cross-model access layer (a second strong model reviews the real diff; read-only multi-host fallback); routes to review, adversarial, delegate, status
 cluster: team
 type: orchestrator
 suggestion:
@@ -18,25 +19,27 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - product-reasoning
+  - meta
 ---
 
 # /team
 
-Top-level orchestrator for the `/team` family — governed **team mode**: the
-depth complement to the council. One strong model builds; a second strong
-model reviews the **real diff with repo access** and iterates. On Claude Code
-hosts every sub-command is a **thin delegation** to the official
+Top-level orchestrator for the `/team` family — governed **team mode**: a
+governed access layer with a read-only multi-host fallback, the depth
+complement to the council. A second strong model reviews the **real diff
+with repo access** and returns its findings. On Claude Code hosts every
+sub-command is a **thin delegation** to the official
 `openai/codex-plugin-cc` plugin (`/codex:*`) — this family adds governance
 (default-off gate, delegate opt-in, quota visibility, fail-closed setup
-checks), never a reimplementation.
+checks), never a reimplementation. An iterated build → review → fix loop is
+**gated future work** — it unlocks only with a positive verdict from the
+pre-registered benchmark (§ No-claims note).
 
 ## What team mode is — and is not
 
 - **Is:** a single strong reviewer running inside the working tree via the
-  Codex CLI under the user's subscription. It reads git state itself,
-  iterates build → review → fix, and returns an opinionated review of the
-  actual change.
+  Codex CLI under the user's subscription. It reads git state itself and
+  returns an opinionated review of the actual change.
 - **Is not:** the council. The council is breadth under a neutrality
   contract — N members see the artefact text only, never the repo, never the
   host's framing. Team mode is the inverse on every axis (table below). The
@@ -46,7 +49,7 @@ checks), never a reimplementation.
 
 | Axis | `/council` | `/team` |
 |---|---|---|
-| Shape | Breadth — N members, one round by default | Depth — one strong reviewer, iterated |
+| Shape | Breadth — N members, one round by default | Depth — one strong reviewer on the real diff |
 | Context | Artefact text only; never the repo, never host framing (neutrality contract) | Full repo access — the reviewer reads git state itself |
 | Cost model | Billable API members by default; USD cost gate | Subscription-authed Codex CLI; daily call quota (`cli_call_budget.max_calls_per_day.openai`) |
 | Model choice | Mid-tier default (cost decision) | Strongest available — `ai_team.model: 'auto'` defers to the CLI default |
@@ -79,7 +82,7 @@ a wrapper is invoked directly.
 | `/team review [--background]` | `/codex:review` | Cross-model review of the current working-tree / staged diff |
 | `/team adversarial <focus>` | `/codex:adversarial-review` | Adversarial cross-model review on a named focus — the escalation rung above the single-model `adversarial-review` skill |
 | `/team delegate <task>` | `/codex:rescue` | Hand a task to the second model as a native worker — the only write-access wrapper; gated behind `ai_team.allow_delegate` |
-| `/team status` | `/codex:status` + ledger line | Plugin job status plus today's `cli_call_budget` openai count |
+| `/team status` | `/codex:status` + quota block | Plugin job status plus the shared openai counter against both ceilings (team + council), naming any blocked path |
 
 ## Dispatch
 
@@ -110,9 +113,11 @@ never an inline reimplementation of the plugin:
 > agent-config doctor --check team
 > ```
 
-On non-Claude-Code hosts the fallback transport (repo-diff bundle via the
-council's `OpenAICliClient`) is a later phase; until it lands, wrappers state
-that plainly and stop — same fail-closed principle.
+On non-Claude-Code hosts the wrappers fall back to a **read-only** transport
+(repo-diff bundle via the council's `OpenAICliClient`) — no plugin job
+control, no background jobs, no delegate write path; the capability delta
+vs. the native plugin is stated in the output. When the codex CLI itself is
+absent, the same fail-closed principle applies: state it plainly and stop.
 
 ## No-claims note
 

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

@@ -9,6 +9,7 @@ sub: e2e-heal
 cluster: tests
 skills: [playwright-testing]
 description: Find, debug, and fix failing Playwright E2E tests
+argument-hint: "[test-file | ci-run-url]"
 suggestion:
   eligible: true
   trigger_description: "fix the failing E2E tests, playwright tests are red"

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

@@ -9,6 +9,7 @@ sub: e2e-plan
 cluster: tests
 skills: [playwright-testing]
 description: Explore the application and create a structured E2E test plan in Markdown
+argument-hint: "[url | feature-area]"
 suggestion:
   eligible: true
   trigger_description: "plan E2E tests for this feature, what should we cover in playwright"

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

@@ -8,6 +8,7 @@ cluster: tests
 sub: execute
 skills: [pest-testing, quality-tools]
 description: Run the project's test suite — stack-adaptive (pest / phpunit / vitest / jest / pytest / …)
+argument-hint: "[file | filter] [--include-e2e] [--include-slow] [--php]"
 suggestion:
   eligible: true
   trigger_description: "run the tests, execute the test suite"

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

@@ -2,6 +2,7 @@
 model_tier: medium
 name: tests
 disable-model-invocation: true
+argument-hint: "[create|execute|e2e-plan|e2e-heal] [args]"
 pack: engineering-base
 tier: 2
 visibility: internal
@@ -34,7 +35,7 @@ commands with a single entry point + sub-command dispatch.
 | `/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.

package/dist/agent-src/commands/update-form-request-messages.md

@@ -7,6 +7,7 @@ visibility: internal
 framework: laravel
 skills: [laravel-validation]
 description: "Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and clean up stale ones."
+argument-hint: "[ClassName | file-path]"
 suggestion:
   eligible: true
   trigger_description: "sync the form request messages, update the validation messages"

package/dist/agent-src/commands/upstream-contribute.md

@@ -6,6 +6,7 @@ tier: 2
 visibility: internal
 skills: [upstream-contribute, skill-writing, learning-to-rule-or-skill]
 description: Contribute a learning, skill, rule, or fix from a consumer project back to the shared agent-config package
+argument-hint: "[path | description]"
 suggestion:
   eligible: true
   trigger_description: "contribute this back to agent-config, upstream this learning"

package/dist/agent-src/commands/video/from-script.md

@@ -7,6 +7,7 @@ visibility: internal
 cluster: video
 sub: from-script
 description: Drive a script end-to-end through the AI video pipeline — scenes → blueprint → image → operator pick → motion → video → stitch. Preview default; --mode commit spends behind the cost gate.
+argument-hint: "<path-to-script.md> [--mode preview|commit] [--max-spend-usd <usd>] [--image-provider <id>] [--video-provider <id>]"
 personas: [hollywood-director, ai-video-technical-director]
 skills: [scene-expander, video-director, pixar-storyteller, character-consistency, motion-choreographer]
 suggestion:
@@ -146,8 +147,8 @@ cost (commit) or summed modeled `cost_estimate` labeled *modeled*
 - **One project per invocation.** Re-running on the same project
   resumes from existing artefacts (skips completed scenes) via the
   ADR-059 resume scan: `scripts/ai-video/lib/resume-scan.sh scan
-  <project> --plan <project>/plan.json` — `green` reused, `stale` /
-  `missing` re-render, `failed` surfaces its `error.json`. State =
+  <project> --plan <project>/plan.json` — `green` is reused, `stale` /
+  `missing` re-render, `failed` surfaces its `error.json`. State is the
   per-scene sentinel set (`prompt.json` with `input_sha256`, the clip,
   `error.json`, `cost.json`) — no central checkpoint file.