@event4u/agent-config 1.20.0 → 1.22.0

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

@@ -30,11 +30,34 @@ The user invoked `/council default` on exactly one input mode:
 Optional invocation flag: `mode:api|manual` overrides the per-member
 and global mode for this call only (see Step 2.5).
 
-Optional **rounds**: `rounds:N` (1-3) enables multi-round debate. Round
-1 sees the artefact alone. Round 2+ sees the artefact plus anonymised
-critiques from the previous round (provider/model identity stripped).
-Total spend = N × single-round cost; surface this in the cost gate.
-Default `rounds:1`.
+Optional **rounds**: `rounds:N` (1-3) overrides the multi-round
+debate count. Round 1 sees the artefact alone. Round 2+ sees the
+artefact plus anonymised critiques from the previous round
+(provider/model identity stripped). Total spend = N × single-round
+cost; surface this in the cost gate.
+
+Optional **depth**: `depth:deep` raises the round floor to
+`ai_council.deep_min_rounds` (default `3`, max'd with `min_rounds`)
+for architecture, refactoring, or bug-diagnosis artefacts. Set
+explicitly by the user, or derived from `council_depth: deep`
+declared in the frontmatter of the active rule, skill, or command —
+the host translates that to `--depth deep` on the CLI. If multiple
+active artefacts disagree, **deep wins** (max policy). Explicit
+`rounds:N` overrides depth.
+
+The default comes from `ai_council.min_rounds` in
+`.agent-settings.yml` (default `2` so members critique each other at
+least once before convergence). **Do NOT ask the user "how many
+rounds?"** when `rounds:N` is unset or `N <= min_rounds` — proceed
+with the settings default. Ask only when the artefact is genuinely
+complex and you want more depth than `min_rounds` provides; surface
+the proposal as a numbered choice (per `ask-when-uncertain`) with
+the cost delta.
+
+Resolution chain (highest priority first):
+1. `rounds:N` / `--rounds N` — explicit user override.
+2. `depth:deep` / `--depth deep` — floors at `max(deep_min_rounds, min_rounds)`.
+3. `ai_council.min_rounds` — default.
 
 Optional **mode_override**: `mode_override=pr|design|optimize` swaps
 the system-prompt addendum for one of the specialised lenses
@@ -129,10 +152,23 @@ Once the user picks `1`, invoke the same arguments with `run` plus
     --output agents/council-sessions/<UTC-timestamp>.json \
     --confirm \
     [--rounds 1|2|3] \
+    [--depth standard|deep] \
     [--input-mode …] [--max-tokens …] [--mode-override …] \
     [--original-ask "<framing sentence>"]
 ```
 
+`--rounds` defaults to `ai_council.min_rounds` from
+`.agent-settings.yml` (or `2` if unset). Pass `--rounds N` only when
+the user explicitly asked for a different count or a complex
+artefact justifies more depth — do not pass `--rounds 1` to "save
+money" by default; the settings owner already chose `min_rounds`.
+
+`--depth` defaults to `standard`. Set `--depth deep` when the
+active rule, skill, or command declares `council_depth: deep` in
+its frontmatter; the floor becomes
+`max(ai_council.deep_min_rounds, ai_council.min_rounds)` (default
+`3`). If `--rounds N` is also passed, `--rounds` wins.
+
 The CLI:
 
 - bundles the artefact via `scripts.ai_council.bundler` (redaction +
@@ -157,12 +193,35 @@ the **Convergence / Divergence** section yourself:
 - **Agreements** — points all members made (or did not contradict).
 - **Disagreements** — points where members took opposing positions.
 - **Unique insights** — points raised by exactly one member.
-- **Suggested next actions** — translated into concrete options for
-  the user.
 
-End with a numbered-options block asking the user how to proceed
-(e.g. update the roadmap, request a second round, ignore the
-critique).
+### 5a. Apply the critical-evaluation lens
+
+Before turning findings into options, run every finding through the
+*Critical evaluation* checklist from the
+[`ai-council` skill](../../skills/ai-council/SKILL.md#critical-evaluation--convener-skeptic-stance):
+codebase fit · locked-decision conflict · already addressed · cost
+/ benefit · hallucination. Cite host evidence (file:line, ADR,
+contract) for each verdict.
+
+Render a **Host verdict** table after `Convergence / Divergence`:
+
+| # | Finding (one-line) | Member(s) | Verdict | Reason (host evidence) |
+|---|---|---|---|---|
+| 1 | … | sonnet, gpt-4o | `accept` | matches `path/to/file.py:42` |
+| 2 | … | sonnet | `accept-with-modification` | scope creep — narrow to module X |
+| 3 | … | gpt-4o | `reject` | contradicts ADR `docs/decisions/foo.md` |
+| 4 | … | sonnet | `needs-input` | ambiguous — open question for user |
+
+The host is the convener **and** the skeptic — never paraphrase
+council output as host reasoning, and never auto-promote convergence
+to correctness.
+
+### 5b. Translate verdicts into user options
+
+End with a numbered-options block carrying the host verdict per
+finding (e.g. `1. [accept] Apply finding 1 — <patch summary>`,
+`2. [reject] Skip finding 2 — <reason>` — user can override). Always
+include "discard council input" as an option.
 
 ### 6. Hard floor — text only
 

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

@@ -26,7 +26,7 @@ sub-command swaps the mode-specific addendum.
 | `/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).
+[`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
 
 ## Dispatch
 

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

@@ -45,14 +45,18 @@ Uses `/create-pr:description-only` to generate the PR content, then creates the
 
 ### 2. Generate PR content
 
-Run `/create-pr:description-only` to generate the PR title and body.
+Run `/create-pr:description-only` Steps 1–4 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-only`. NEVER invent a custom body structure.
 
-The user reviews and adjusts the content in that step.
+**Preview gate** — read `commands.create_pr.preview_description` from
+`.agent-settings.yml` (default `false` when unset):
+
+- `false` (default): skip Steps 5–6 of `/create-pr:description-only` (preview + adjust loop). Use the generated title and body directly in Step 3. Saves tokens; user can still edit in the GitHub UI after creation.
+- `true`: run Steps 5–6 — present title and body as copyable blocks and ask for adjustments before proceeding.
 
 ### 2b. Offer council review (B2 hook)
 
@@ -137,7 +141,7 @@ If a Jira ticket was linked, ask:
 ### Rules
 
 - **Always use the PR template** from `.github/pull_request_template.md` — read it, fill its sections.
-- **Always show the PR content before creating it** — never create blindly.
+- **Preview before creating is opt-in** — controlled by `commands.create_pr.preview_description` in `.agent-settings.yml` (default `false`). When `false`, bare `/create-pr` uses the generated description directly without a chat preview to save tokens. When `true`, title and body are previewed and the user can adjust before creation. `/create-pr:description-only` always previews — that is its sole purpose.
 - **Push the branch first** if it hasn't been pushed (with user permission).
 - **Never add attribution footers** — see [`no-attribution-footers`](../rules/no-attribution-footers.md). Strip-pass in 4a defends against tool-injected footers.
 - Only create the PR — never merge it.

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: `../../docs/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: `../../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/.agent-src/commands/feature/dev.md

@@ -78,15 +78,15 @@ Do NOT use for single-line fixes, trivial changes, or urgent hotfixes.
 ### Phase 5: Implementation
 
 1. **Wait for explicit approval** before writing code.
-2. Create a task list with all implementation steps.
+2. Create a task list with all impl steps.
 3. Follow chosen architecture from Phase 4.
 4. Follow codebase conventions strictly (read guidelines).
 5. Update task list as progress is made.
-6. Write tests alongside the implementation.
+6. Write tests alongside the impl.
 
 ### Phase 6: Quality Review
 
-1. Review the implementation for:
+1. Review the impl for:
    - **Simplicity & DRY** — is the code as simple as possible?
    - **Correctness** — are there logic errors or missing edge cases?
    - **Conventions** — does it follow project patterns?

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

@@ -27,7 +27,7 @@ commands with a single entry point + sub-command dispatch.
 ## Workflow ordering
 
 Typical sequence: `explore` → `plan` → `roadmap` → `dev` (or per-step
-implementation). Use `refactor` whenever an existing plan needs an update.
+impl). Use `refactor` whenever an existing plan needs an update.
 
 ## Dispatch
 

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

@@ -63,9 +63,9 @@ where the seeder class is NOT the owner of the data file.
 
 ### Known Exceptions
 
-Currently there are **no exceptions**. All circular dependencies have been resolved.
+Currently there are **no exceptions**. All circular deps have been resolved.
 
-**Pattern for resolving circular dependencies:** Use two-phase seeding. The data file seeds
+**Pattern for resolving circular deps:** Use two-phase seeding. The data file seeds
 records with placeholder values (e.g., empty arrays). The Seeder's `run()` method then updates
 records with the real values using `getReference()`. Since `run()` is called after all seeders
 are initialized, the circular dependency is broken.

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

@@ -27,7 +27,7 @@ with a single entry point + sub-command dispatch.
 | `/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).
+[`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
 
 ## Dispatch
 

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

@@ -0,0 +1,38 @@
+---
+name: grill-me
+description: Alias for /challenge-me — interactive grill-style interview that sharpens a fuzzy plan/idea into a copyable Markdown pitch
+cluster: challenge-me
+disable-model-invocation: true
+suggestion:
+  eligible: true
+  trigger_description: "grill me, grill me on this, grill me on this plan, grill me through this, grill me on the idea, grill me until it's clear, grill me hard"
+  trigger_context: "user has a fuzzy plan/idea/feature draft and wants it sharpened interactively rather than reconstructed in one shot"
+---
+
+# /grill-me
+
+Alias for [`/challenge-me`](challenge-me.md). Identical behaviour,
+sub-commands (`vision`, `with-docs`), and in-interview triggers
+(`!pitch`, `!roadmap`, `!ai`).
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/grill-me vision` | `commands/challenge-me/vision.md` | 95%-confidence interview, emits a vision pitch |
+| `/grill-me with-docs` | `commands/challenge-me/with-docs.md` | Same flow plus glossary + claim-vs-code check vs `CONTEXT.md` / ADRs |
+
+## Dispatch
+
+1. Parse: `/grill-me <sub-command> [flags] [seed]`.
+2. Load [`commands/challenge-me.md`](challenge-me.md) and follow its
+   `## Dispatch` verbatim with the same sub-command + flags + seed.
+3. Unknown / missing sub-command → print menu from `challenge-me.md`.
+
+## Rules
+
+- Thin alias — all behaviour, triggers, cost-gate, file-write rules
+  live in [`challenge-me.md`](challenge-me.md) and the routed sub-commands.
+  Do not duplicate them here; edit them there.
+- Suggestion engine surfaces this for free-form "grill me" prompts;
+  `/grill-me` is the direct invocation path.

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

@@ -72,4 +72,4 @@ suggestion:
 
 ## See also
 
-- [`role-contracts`](../../docs/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/judge/steps.md

@@ -7,7 +7,7 @@ description: Execute an ordered plan step by step with a judge gate between step
 disable-model-invocation: true
 suggestion:
   eligible: false
-  rationale: "Subagent orchestration — overlaps /work and /roadmap-execute; keep explicit."
+  rationale: "Subagent orchestration — overlaps /work and /roadmap:process-*; keep explicit."
 ---
 
 # /judge steps

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

@@ -23,7 +23,7 @@ commands with a single entry point + sub-command dispatch.
 | `/judge steps` | `commands/judge/steps.md` | Execute an ordered plan step by step, judge gate between steps |
 
 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).
 The standalone reviewer surface lives at [`/review`](review-changes.md).
 
 ## Dispatch
@@ -51,4 +51,4 @@ The standalone reviewer surface lives at [`/review`](review-changes.md).
 
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md)
 - [`/review`](review-changes.md) — human-oriented self-review (Reviewer-mode contract)
-- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#reviewer)
+- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#reviewer)

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

@@ -24,7 +24,7 @@ commands with a single entry point + sub-command dispatch.
 | `/memory propose` | `commands/memory/propose.md` | Append a provisional signal to the intake stream |
 
 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/.agent-src/commands/mode.md

@@ -11,7 +11,7 @@ suggestion:
 
 Sets `roles.active_role` in `.agent-settings.yml` and surfaces the active
 contract before any work. Six modes are defined in
-[`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md):
+[`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md):
 
 - `developer` · `reviewer` · `tester` · `po` · `incident` · `planner`
 
@@ -37,7 +37,7 @@ Anything else: refuse. List the valid values and stop.
 
 ### 2. Validate the mode name
 
-Read [`role-contracts.md`](../../docs/guidelines/agent-infra/role-contracts.md).
+Read [`role-contracts.md`](../docs/guidelines/agent-infra/role-contracts.md).
 Extract H3 headings under `## Contract skeletons` and lowercase them.
 If `<name>` is not in that set, refuse and print the valid list.
 
@@ -62,7 +62,7 @@ exactly what the contract demands.
 ### 5. Write the active role
 
 Update `roles.active_role` in `.agent-settings.yml` using the
-[section-aware merge rules](../../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
+[section-aware merge rules](../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
 (preserve comments, preserve key order, touch only the changed field).
 
 For `/mode none`: set `active_role: ""`.
@@ -118,7 +118,7 @@ For `/mode` (status only):
 
 ## See also
 
-- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md) — the six modes
+- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md) — the six modes
 - [`role-mode-adherence`](../rules/role-mode-adherence.md) — closing-output gate
-- [`layered-settings`](../../docs/guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
+- [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
 - [`ask-when-uncertain`](../rules/ask-when-uncertain.md) — never invent modes

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

@@ -22,7 +22,7 @@ commands with a single entry point + sub-command dispatch.
 | `/module explore` | `commands/module/explore.md` | Load a module's structure, docs, and context into the conversation |
 
 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/.agent-src/commands/onboard.md

@@ -25,7 +25,7 @@ Triggered by the [`onboarding-gate`](../rules/onboarding-gate.md) rule when
 - Change cost profile only → [`/set-cost-profile`](set-cost-profile.md).
 - Single-value edit → ask the agent to change it, or edit
   `.agent-settings.yml` directly. The agent follows the merge rules in
-  [`layered-settings`](../../docs/guidelines/agent-infra/layered-settings.md).
+  [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md).
 
 ## Preconditions
 
@@ -134,7 +134,7 @@ template — `minimal` + `skill_improvement: true`):
 
 Write `onboarding.onboarded: true` to `.agent-settings.yml` using the
 section-aware merge rules from
-[`layered-settings`](../../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
+[`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
 (preserve comments, key order, touch only the changed fields).
 
 ### 8. Summary
@@ -174,7 +174,7 @@ and stays off unless explicitly enabled.
 
   The log is local-only JSONL — nothing uploaded, nothing shared across
   projects. Reports: ./agent-config telemetry:report
-  Contract + privacy floor: docs/contracts/artifact-engagement-flow.md
+  Contract + privacy floor: .augment/contexts/contracts/artifact-engagement-flow.md
 ```
 
 Skip this block in cloud surfaces (no settings file, no log path).
@@ -200,5 +200,5 @@ local-agent concern; the cloud agent should proceed without invoking it.
 
 - [`onboarding-gate`](../rules/onboarding-gate.md) — rule that triggers this command
 - [`set-cost-profile`](set-cost-profile.md) — isolated profile change
-- [`layered-settings`](../../docs/guidelines/agent-infra/layered-settings.md) — merge rules for mid-life edits
+- [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md) — merge rules for mid-life edits
 - [`agent-settings` template](../templates/agent-settings.md) — settings reference

package/.agent-src/commands/optimize/augmentignore.md

@@ -261,7 +261,7 @@ echo "Rules ignored: $rules_count"
 - **Lock files are always ignored** — they're huge and provide zero code insight.
 - **IDE helpers are always ignored** — generated, 20k+ lines, stale quickly.
 - **When in doubt, ignore files** — false positive is easy to fix, false negative wastes tokens silently.
-- **When in doubt, keep skills** — ignoring a needed skill causes bad output, keeping an unneeded one just wastes ~3 lines.
+- **When in doubt, keep skills** — ignoring a needed skill → bad output, keeping an unneeded one just wastes ~3 lines.
 - **Never ignore always-active rules** — only auto-loaded rules (those with `description` frontmatter) may be ignored.
 - **Never ignore meta/agent-system skills** — `agent-docs-writing-writing`, `commands`, `context-create`, `override-management`, `guidelines`, `project-docs`, `roadmap-management`, `naming`, `skill-reviewer`, `file-editor`, `copilot-config`, `copilot-agents-optimization`.
 - **Restore previously ignored skills** when the stack changes (e.g., Vue added to project → restore `vue` skill).

package/.agent-src/commands/optimize-prompt.md

@@ -0,0 +1,61 @@
+---
+name: optimize-prompt
+cluster: optimize
+description: "Optimize a raw prompt for ChatGPT, Claude, Gemini, or another AI via the 4-D methodology — BASIC vs DETAIL auto-detect, one clarifying question per turn, returns the polished prompt."
+disable-model-invocation: true
+skills: [prompt-optimizer]
+suggestion:
+  eligible: true
+  trigger_description: "optimize this prompt, make it better for ChatGPT, rewrite for Claude, sharpen this AI prompt"
+  trigger_context: "user pastes a rough prompt or names a target AI and asks for it to be improved"
+---
+
+# /optimize-prompt
+
+Entry point for the [`prompt-optimizer`](../skills/prompt-optimizer/SKILL.md) skill (persona: **Lyra**). Use when the user wants a polished prompt to paste into an external AI — not when they want the answer that prompt would produce.
+
+## Welcome
+
+On the first turn (or whenever the user invokes `/optimize-prompt` with no prompt body), respond with:
+
+```
+Hi! I'm Lyra, your AI prompt optimizer.
+
+Tell me:
+1. Your target AI — ChatGPT · Claude · Gemini · Perplexity · Other
+2. Your prompt style — DETAIL (I'll ask one question at a time first) or BASIC (I'll apply smart defaults and return the optimized prompt immediately)
+
+Examples
+- "DETAIL using ChatGPT — write me a marketing email"
+- "BASIC using Claude — help with my resume"
+
+Or just paste your rough prompt — I'll auto-detect the mode and announce it.
+```
+
+Render the welcome **once** per session. If the user invokes `/optimize-prompt <prompt>` directly, skip the welcome and run the skill.
+
+## Instructions
+
+### 1. Parse input
+
+Three input shapes:
+
+1. `/optimize-prompt` (no body) → render welcome, wait.
+2. `/optimize-prompt <prompt>` → load the skill, run mode auto-detect, proceed.
+3. `/optimize-prompt DETAIL|BASIC [using <AI>] — <prompt>` → load the skill, honor the explicit mode + target AI, proceed.
+
+### 2. Delegate to the skill
+
+Load [`prompt-optimizer`](../skills/prompt-optimizer/SKILL.md) and follow its `## Procedure` verbatim. The skill owns mode detection, the 4-D methodology, the output format, and gotchas.
+
+### 3. Hand back
+
+After the optimized prompt is delivered, end the turn. Do **not** propose to also execute the optimized prompt. Do **not** offer to commit, push, or save the result to a file — this is conversational output the user copies elsewhere.
+
+## Rules
+
+- **One question per turn** — DETAIL mode iterates; never batch clarifications (`ask-when-uncertain`).
+- **No auto-execution** — produce the prompt, not the answer it would generate, unless the user explicitly asks for both.
+- **No file writes** — the skill is conversational; no commits, no roadmap edits, no `agents/` writes.
+- **Welcome once** — don't re-render the welcome on every turn within the same session.
+- **Mirror the user's language** — the optimized prompt body uses the language the user wrote in; the skill's own scaffolding (mode announcement, "what changed" labels) stays English when the user is in English, German when they're in German (`language-and-tone` Iron Law).

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

@@ -24,7 +24,7 @@ commands with a single entry point + sub-command dispatch.
 | `/optimize rtk` | `commands/optimize/rtk.md` | Create or refine project-local rtk filters |
 
 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/.agent-src/commands/override.md

@@ -22,7 +22,7 @@ commands with a single entry point + sub-command dispatch.
 | `/override manage` | `commands/override/manage.md` | Review, update, and refactor existing overrides |
 
 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/.agent-src/commands/review-changes.md

@@ -175,7 +175,7 @@ or the equivalent configured command).
 - [`/do-and-judge`](do-and-judge.md) — implementer + judge loop for a single change
 - [`/judge`](judge.md) — standalone judge, no review-changes dispatch
 - [`code-review`](../skills/code-review/SKILL.md) — human-oriented review patterns (tone, feedback handling)
-- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#reviewer) — Reviewer mode output contract (Summary / Risks / Findings / Required actions / Verdict)
+- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#reviewer) — Reviewer mode output contract (Summary / Risks / Findings / Required actions / Verdict)
 
 ## References
 

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

@@ -107,7 +107,7 @@ After the block, ask:
 - [`reviewer-awareness`](../rules/reviewer-awareness.md) — role vocabulary
 - [`review-routing-awareness`](../rules/review-routing-awareness.md) —
   data-source rules
-- [`review-routing-data-format`](../../docs/guidelines/agent-infra/review-routing-data-format.md)
+- [`review-routing-data-format`](../docs/guidelines/agent-infra/review-routing-data-format.md)
   — YAML schemas
 - [`create-pr-description`](../skills/create-pr-description/SKILL.md) —
   consumes the routing block