@ionivetech/mugiwara 0.6.3 → 0.6.5

package/.claude-plugin/marketplace.json

@@ -5,13 +5,13 @@
   },
   "metadata": {
     "description": "The Straw Hat crew for AI agents",
-    "version": "0.6.3"
+    "version": "0.6.5"
   },
   "plugins": [
     {
       "name": "mugiwara",
       "description": "The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, healing.",
-      "version": "0.6.3",
+      "version": "0.6.5",
       "source": "./"
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "mugiwara",
   "displayName": "Mugiwara",
-  "version": "0.6.3",
+  "version": "0.6.5",
   "description": "The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, healing.",
   "author": {
     "name": "ionivetech"

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mugiwara",
-  "version": "0.6.3",
+  "version": "0.6.5",
   "description": "The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, healing.",
   "author": {
     "name": "ionivetech"
@@ -14,5 +14,52 @@
     "workflow",
     "multi-agent"
   ],
-  "skills": "./content/skills/"
+  "skills": "./content/skills/",
+  "metadata": {
+    "skills": [
+      "mugiwara-agent-security",
+      "mugiwara-backend",
+      "mugiwara-brainstorm",
+      "mugiwara-checkpoint",
+      "mugiwara-claim-audit",
+      "mugiwara-context-budget",
+      "mugiwara-contract-first",
+      "mugiwara-execution",
+      "mugiwara-frontend",
+      "mugiwara-gates",
+      "mugiwara-git",
+      "mugiwara-healing",
+      "mugiwara-lessons",
+      "mugiwara-orchestration",
+      "mugiwara-planning",
+      "mugiwara-pr",
+      "mugiwara-quality",
+      "mugiwara-resume",
+      "mugiwara-review",
+      "mugiwara-root-cause",
+      "mugiwara-security",
+      "mugiwara-ship",
+      "mugiwara-sunset",
+      "mugiwara-testcases",
+      "mugiwara-workflow",
+      "using-mugiwara"
+    ],
+    "agents": [
+      "brook-healing",
+      "chopper-checkpoint",
+      "eval-runner",
+      "franky-gates",
+      "jinbe-security",
+      "luffy-orchestrator",
+      "memory-keeper",
+      "nami-planner",
+      "onboarding-guide",
+      "resume-coordinator",
+      "robin-reviewer",
+      "sanji-quality",
+      "skeptic-verifier",
+      "usopp-brainstorm",
+      "zoro-execution"
+    ]
+  }
 }

package/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "mugiwara",
   "displayName": "Mugiwara",
   "description": "The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, healing.",
-  "version": "0.6.3",
+  "version": "0.6.5",
   "author": {
     "name": "ionivetech"
   },
@@ -15,5 +15,52 @@
     "workflow",
     "multi-agent"
   ],
-  "skills": "./content/skills/"
+  "skills": "./content/skills/",
+  "metadata": {
+    "skills": [
+      "mugiwara-agent-security",
+      "mugiwara-backend",
+      "mugiwara-brainstorm",
+      "mugiwara-checkpoint",
+      "mugiwara-claim-audit",
+      "mugiwara-context-budget",
+      "mugiwara-contract-first",
+      "mugiwara-execution",
+      "mugiwara-frontend",
+      "mugiwara-gates",
+      "mugiwara-git",
+      "mugiwara-healing",
+      "mugiwara-lessons",
+      "mugiwara-orchestration",
+      "mugiwara-planning",
+      "mugiwara-pr",
+      "mugiwara-quality",
+      "mugiwara-resume",
+      "mugiwara-review",
+      "mugiwara-root-cause",
+      "mugiwara-security",
+      "mugiwara-ship",
+      "mugiwara-sunset",
+      "mugiwara-testcases",
+      "mugiwara-workflow",
+      "using-mugiwara"
+    ],
+    "agents": [
+      "brook-healing",
+      "chopper-checkpoint",
+      "eval-runner",
+      "franky-gates",
+      "jinbe-security",
+      "luffy-orchestrator",
+      "memory-keeper",
+      "nami-planner",
+      "onboarding-guide",
+      "resume-coordinator",
+      "robin-reviewer",
+      "sanji-quality",
+      "skeptic-verifier",
+      "usopp-brainstorm",
+      "zoro-execution"
+    ]
+  }
 }

package/.kimi-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mugiwara",
-  "version": "0.6.3",
+  "version": "0.6.5",
   "description": "The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, healing.",
   "author": {
     "name": "ionivetech"
@@ -14,5 +14,52 @@
     "workflow",
     "multi-agent"
   ],
-  "skills": "./content/skills/"
+  "skills": "./content/skills/",
+  "metadata": {
+    "skills": [
+      "mugiwara-agent-security",
+      "mugiwara-backend",
+      "mugiwara-brainstorm",
+      "mugiwara-checkpoint",
+      "mugiwara-claim-audit",
+      "mugiwara-context-budget",
+      "mugiwara-contract-first",
+      "mugiwara-execution",
+      "mugiwara-frontend",
+      "mugiwara-gates",
+      "mugiwara-git",
+      "mugiwara-healing",
+      "mugiwara-lessons",
+      "mugiwara-orchestration",
+      "mugiwara-planning",
+      "mugiwara-pr",
+      "mugiwara-quality",
+      "mugiwara-resume",
+      "mugiwara-review",
+      "mugiwara-root-cause",
+      "mugiwara-security",
+      "mugiwara-ship",
+      "mugiwara-sunset",
+      "mugiwara-testcases",
+      "mugiwara-workflow",
+      "using-mugiwara"
+    ],
+    "agents": [
+      "brook-healing",
+      "chopper-checkpoint",
+      "eval-runner",
+      "franky-gates",
+      "jinbe-security",
+      "luffy-orchestrator",
+      "memory-keeper",
+      "nami-planner",
+      "onboarding-guide",
+      "resume-coordinator",
+      "robin-reviewer",
+      "sanji-quality",
+      "skeptic-verifier",
+      "usopp-brainstorm",
+      "zoro-execution"
+    ]
+  }
 }

package/.opencode/mugiwara-helpers.mjs

@@ -93,10 +93,14 @@ export const DEFAULT_CONFIG_LINES = [
   'mode=guided',
   'branch=feature/{type}-{issue}-{slug}',
   'commit=conventional',
+  'auto_commit=on',
   'coverage_new=90',
   'coverage_modified=80',
   'review_depth=full',
   'quality_depth=full',
+  'delegate_threshold=60',
+  'heal_max_cycles=3',
+  'verbosity=normal',
 ];
 
 // Idempotent: writes the full default config only when .mugiwara/config is

package/.opencode/plugins/mugiwara.mjs

@@ -6,6 +6,11 @@
 // single export because OpenCode's legacy loader calls every exported function
 // as a plugin (same constraint ponytail documents).
 //
+// Crew COLORS come from references/wave-banners.md (single source, shared
+// references dir); the CREW map below is the cold-path
+// fallback only. Temperature/steps stay here (runtime tuning, not banner
+// material).
+//
 // Install: add to opencode.json
 //   { "plugin": ["@ionivetech/mugiwara"] }
 // or from the git repo:
@@ -22,26 +27,48 @@ const contentDir = join(__dirname, '..', '..', 'content');
 const skillsDir = join(contentDir, 'skills');
 const agentsDir = join(contentDir, 'agents');
 
-const ANNOUNCE =
-  "Mugiwara crew available. The workflow auto-activates for non-trivial requests — no need to call `/using-mugiwara` at session start (it is an optional router). Run the crew pipeline inline in the main conversation: embody ONE crew role at a time using its skill, wait for its report, then move to the next. Never Task-dispatch a crew member — the crew runs in the main thread; subagents only for [PARALLEL] task batches, concurrent review/security, and independent re-run checks. Progress shows as checkpoint reports at wave/stage boundaries, pausing on failure or risk. Switch mode with `/mugiwara` (guided|semi|auto). See skills/mugiwara-workflow.";
-
+// Colors are fallbacks — the wave-banners table is the source of truth.
 const CREW = {
   'luffy-orchestrator': { color: '#ef4444', temperature: 0.2, steps: 30 },
-  'usopp-brainstorm': { color: '#f59e0b', temperature: 0.6, steps: 30 },
+  'usopp-brainstorm': { color: '#b45309', temperature: 0.6, steps: 30 },
   'nami-planner': { color: '#f97316', temperature: 0.2, steps: 30 },
   'zoro-execution': { color: '#22c55e', temperature: 0.1, steps: 50 },
-  'chopper-checkpoint': { color: '#3b82f6', temperature: 0.1, steps: 30 },
-  'sanji-quality': { color: '#a855f7', temperature: 0.1, steps: 40 },
+  'chopper-checkpoint': { color: '#60a5fa', temperature: 0.1, steps: 30 },
+  'sanji-quality': { color: '#facc15', temperature: 0.1, steps: 40 },
   'franky-gates': { color: '#06b6d4', temperature: 0.1, steps: 40 },
   'robin-reviewer': { color: '#8b5cf6', temperature: 0.2, steps: 30 },
   'jinbe-security': { color: '#6366f1', temperature: 0.2, steps: 30 },
-  'brook-healing': { color: '#ec4899', temperature: 0.1, steps: 30 },
+  'brook-healing': { color: '#2dd4bf', temperature: 0.1, steps: 30 },
   'skeptic-verifier': { color: '#64748b', temperature: 0.1, steps: 30 },
   'eval-runner': { color: '#14b8a6', temperature: 0.2, steps: 30 },
   'resume-coordinator': { color: '#d97706', temperature: 0.2, steps: 30 },
   'memory-keeper': { color: '#d946ef', temperature: 0.2, steps: 30 },
+  'onboarding-guide': { color: '#0ea5e9', temperature: 0.3, steps: 15 },
 };
 
+// Read the crew color table (single source of truth, shared references/).
+// Returns {} on any failure — callers fall back to the CREW map. The regex
+// anchors the exact table shape: | agent-id | role | hex | ansi-256 | emoji |
+function readBannerColors() {
+  try {
+    const path = join(__dirname, '..', '..', 'references', 'wave-banners.md');
+    if (!existsSync(path)) return {};
+    const text = readFileSync(path, 'utf8');
+    // null-prototype: agent ids are trusted repo content, but a future
+    // `__proto__` id must never write the object's prototype
+    const colors = Object.create(null);
+    for (const m of text.matchAll(/^\| ([\w-]+) \| [^|]+ \| (#[0-9a-f]{6}) \| (\d+) \| (\S+) \|\r?$/gm)) {
+      colors[m[1]] = m[2];
+    }
+    return colors;
+  } catch {
+    return {};
+  }
+}
+
+const ANNOUNCE =
+  "Mugiwara crew available. The workflow auto-activates for non-trivial requests — no need to call `/using-mugiwara` at session start (it is an optional router). Run the crew pipeline inline in the main conversation: embody ONE crew role at a time using its skill, wait for its report, then move to the next. Never Task-dispatch a crew member — the crew runs in the main thread; subagents only for [PARALLEL] task batches, concurrent review/security, and independent re-run checks. Progress shows as checkpoint reports at wave/stage boundaries, pausing on failure or risk. Switch mode with `/mugiwara` (guided|semi|auto). See skills/mugiwara-workflow.";
+
 function parseFrontmatter(text) {
   const m = text.match(/^---\r?\n([\s\S]*?)\r?\n---\r?\n?/);
   if (!m) throw new Error('Missing frontmatter fence (---)');
@@ -68,6 +95,7 @@ function permissionFromScope(scope) {
 
 function readAgents(stepsEnabled = true) {
   const agents = {};
+  const bannerColors = readBannerColors();
   let files;
   try {
     files = readdirSync(agentsDir).filter((f) => f.endsWith('.md'));
@@ -99,6 +127,11 @@ function readAgents(stepsEnabled = true) {
       agents[name] = { ...agents[name], ...rest };
       if (stepsEnabled) agents[name] = { ...agents[name], steps };
     }
+    // color comes from the wave-banners table (single source); CREW fallback
+    // covers agents the table does not list (and vice versa)
+    if (bannerColors[name] || CREW[name]) {
+      agents[name] = { ...agents[name], color: bannerColors[name] ?? CREW[name].color };
+    }
     const perm = permissionFromScope(parsed.data['write-scope']);
     if (perm && agents[name].mode === 'subagent') agents[name].permission = perm;
   }

package/AGENTS.md

@@ -106,6 +106,17 @@ class.
 
 No PR merges without all green CI.
 
+### Assertion rules
+
+- **No `expect()` inside a conditional** unless the condition is itself a
+  declared invariant (e.g. `if (tier === 3)`). An assertion that can be skipped
+  is not an assertion. Enforced by `validate-content.ts`.
+- **Type checks are not coverage.** `typeof x === 'number'` passes on `0`.
+  `Array.isArray(x)` passes on `[]`. Assert the value the fixture was built to
+  produce.
+- Every field in `state.json` has a fixture assertion with a non-trivial
+  expected value.
+
 ## Skill standards
 
 Every skill is `content/skills/<name>/SKILL.md`:

package/README.md

@@ -245,10 +245,14 @@ Switch mode any time: `/mugiwara guided | semi | auto`. Or edit `.mugiwara/confi
 | `mode`              | guided                          | guided / semi / auto                           |
 | `branch`            | `feature/{type}-{issue}-{slug}` | Branch naming                                  |
 | `commit`            | conventional                    | conventional / gitmoji / plain                 |
+| `auto_commit`       | on                              | on / off — off disables commit+push in guided/semi |
 | `coverage_new`      | 90                              | Coverage threshold for new files (%)           |
 | `coverage_modified` | 80                              | Coverage threshold for modified files (%)      |
 | `review_depth`      | full                            | full / standard / quick — Robin's review depth |
 | `quality_depth`     | full                            | full / standard / quick — Sanji's check depth  |
+| `delegate_threshold`| 60                              | % of token budget at which remaining tasks dispatch to workers |
+| `heal_max_cycles`   | 3                               | Max heal-loop cycles before human escalation    |
+| `verbosity`         | normal                          | normal / full — how much the crew echoes. `normal` hides investigation steps (reads, greps) and file contents; edits, results, decisions stay visible. `full` echoes everything. Never suppresses decisions, questions, blockers, or lane rises |
 
 Set via `/mugiwara onboard` or edit directly. Unknown keys ignored. Project
 config (`.mugiwara/config`) overrides global (`~/.mugiwara/config`).
@@ -415,6 +419,8 @@ Uninstall: `mugiwara uninstall`
 All platforms get the full crew — 12 agents (+3 internal), 26 skills.
 Enforcement depth varies by harness; see the [harness matrix](docs/reference/harness-matrix.md).
 
+→ [How the skills stay small: three-layer disclosure](docs/reference/skill-anatomy.md)
+
 → [Per-platform guides](docs/install/index.md)
 
 ## Update
@@ -452,7 +458,7 @@ mugiwara reset --keep-logs                    # wipe state, keep lessons
 
 **Start here:** [Getting started](docs/getting-started.md) · [What mugiwara replaces](docs/concepts/comparison.md)
 
-**Concepts:** [Workflow](docs/concepts/workflow.md) · [Lanes](docs/concepts/lanes.md) · [Modes](docs/concepts/modes.md) · [Execution model](docs/concepts/execution-model.md) · [Git strategy](docs/concepts/git-strategy.md) · [Config](docs/concepts/config.md) · [Cost](docs/concepts/cost.md) · [Audit trail](docs/concepts/audit-trail.md)
+**Concepts:** [Workflow](docs/concepts/workflow.md) · [Lanes](docs/concepts/lanes.md) · [Modes](docs/concepts/modes.md) · [Execution model](docs/concepts/execution-model.md) · [Git strategy](docs/concepts/git-strategy.md) · [Config](docs/concepts/config.md) · [Cost](docs/concepts/cost.md) · [Audit trail](docs/concepts/audit-trail.md) · [Security](docs/concepts/security.md)
 
 **Crew:** [Agents](docs/concepts/agents.md) · [Skills](docs/concepts/skills.md)
 
@@ -464,6 +470,20 @@ mugiwara reset --keep-logs                    # wipe state, keep lessons
 
 **Roadmap:** [ROADMAP.md](ROADMAP.md)
 
+## What is measured, and what is not
+
+| Claim | Status |
+|---|---|
+| Retrieval routing rank-1 | **93.5%**, 181 probes, offline, in CI |
+| Reference pointers resolve | **66/66**, 3 tiers, in CI |
+| Lane constants match content load | **verified**, in CI |
+| Write-scope enforcement | **opencode only** — rules-based elsewhere |
+| Cross-harness mission behavior | **12/12 platforms** — 9 rules-dir installs + 3 marketplace manifests, in CI |
+| Outcome vs other approaches | **not measured** — see roadmap |
+
+Numbers here are produced by `bun run gate`. Nothing in this table is an
+estimate.
+
 ## License
 
 MIT. Copyright (c) 2026 ionivetech.

package/content/agents/zoro-execution.md

@@ -31,7 +31,7 @@ Wave 3 of `mugiwara-workflow`, with the plan doc path.
 ## Rules
 
 1. Follow `mugiwara-execution` exactly (ingestion, dispatch rules, per-task discipline).
-2. Before touching code, follow the mode's branch/commit rule (per mode config): `guided` ASKS THE USER (auto branch for the mission or current branch; auto commit per task or user-controlled checkpoints); `semi`/`auto` auto-create the mission branch per the config `branch` key and auto-commit per task in the config `commit` style — no ask. Record the mode + branch + commit style in the decision log (`.mugiwara/logs/`) and todos. State-mutating consent still applies in every mode.
+2. Before touching code, follow the mode's branch/commit rule (per mode config): `guided` ASKS THE USER (auto branch for the mission or current branch; auto commit per task or user-controlled checkpoints); `semi` auto-creates the mission branch per the config `branch` key and auto-commits per task in the config `commit` style — no ask; `auto` same but commits ALWAYS. `auto_commit=off` (config, default on): guided and semi leave all changes uncommitted for the user — no commits, no push; auto mode ignores it. Record the mode + branch + commit style + auto_commit in the decision log (`.mugiwara/logs/`) and todos. State-mutating consent still applies in every mode.
 3. Sequential tasks and chains run INLINE in the main thread — no subagent round-trips for ordered work. Only `[PARALLEL]` task batches dispatch WORKER subagents (one task per worker); never another crew member; return your execution report inline to the conversation, which routes to Chopper.
 4. Every task done = evidence attached (command output / file inspection); run acceptance criteria, do not assert them.
 5. Apply `mugiwara-git` as you go: atomic commits per LOGICAL task (when auto-commit is on) — a task is a meaningful unit of work, not a micro-step; adjacent trivial changes fold into the neighboring task's commit. Save-points before risky work, commit style matched to the repo history.

package/content/skills/mugiwara-checkpoint/SKILL.md

@@ -65,5 +65,6 @@ TRUST NOTHING; VERIFY EVERYTHING. No evidence, no pass — and the evidence must
 - Commits containing undeclared files, or missing declared files.
 - A DoD axis passed with no evidence.
 - Any urge to edit code instead of reporting the finding.
+- Echoing raw output when `verbosity=normal` — summarize and cite the evidence path.
 
 All mean: the audit is incomplete. Finish it before issuing the verdict.

package/content/skills/mugiwara-execution/SKILL.md

@@ -14,12 +14,12 @@ Execute the plan exactly. No silent reordering, no skipping steps, no "close eno
 
 ## Ask before working
 
-- `guided`: before touching any code, ASK THE USER — auto branch (dedicated mission branch, recommended, keeps `main` clean) or work on the current branch; auto commit per task or commit at user-controlled checkpoints.
-- `semi`/`auto`: auto-create the mission branch per the config `branch` key (default `feature/{type}-{issue}-{slug}`) and auto-commit per task using the config `commit` style (default conventional). No branch/commit ask. Record mode + branch + commit style in the decision log (`.mugiwara/logs/YYYY-MM-DD-<mission>.md`) and in `.mugiwara/results/<mission>/todos.md`.
+- `guided`: before touching any code, ASK THE USER — auto branch (dedicated mission branch, recommended, keeps `main` clean) or work on the current branch; auto commit per task or commit at user-controlled checkpoints. With `auto_commit=off`: the branch ask stays, the commit question is skipped — changes stay uncommitted.
+- `semi`: auto-create the mission branch per the config `branch` key; auto-commit per task in the config `commit` style ONLY when `auto_commit=on` (default). Off → leave every task's changes uncommitted; the user commits manually.
+- `auto`: auto-create the branch and auto-commit per task ALWAYS — `auto_commit=off` has no effect in auto mode.
+Record mode + branch + commit style + `auto_commit` in the decision log (`.mugiwara/logs/YYYY-MM-DD-<mission>.md`) and in `.mugiwara/results/<mission>/todos.md` — every mode.
 
-Code to the installed version's docs, not memory: `_shared/references/source-grounding.md`.
-
-The plan doc stays clean — never edit it during execution except through Nami. If the user says no auto-commit in `guided`, still run every acceptance check and leave the diff staged or presented for approval. State-mutating consent is NOT covered by this rule — it still applies in every mode. One-task-one-commit, save-points, and atomic-commit rules hold unchanged in every mode.
+Code to the installed version's docs, not memory: `_shared/references/source-grounding.md`. The plan doc stays clean — never edit it during execution except through Nami. If the user says no auto-commit in `guided`, still run every acceptance check and leave the diff staged or presented for approval. State-mutating consent is NOT covered by this rule — it still applies in every mode. One-task-one-commit, save-points, and atomic-commit rules hold unchanged in every mode.
 
 ## Todo list first
 
@@ -28,9 +28,7 @@ Before touching code:
 1. Create `.mugiwara/results/<mission>/todos.md` — one checkbox per task, derived from the plan.
 2. Check each box off only when the task completes, WITH its evidence link (`[path](relative/path)`, clickable).
 3. Re-check the whole list after each task and after each batch; unmarked boxes mean the mission is not done.
-4. Mirror every change into the host's native todo tool (`todowrite` on
-   opencode; `TaskUpdate` on Claude Code; none on tier 2/3 — plan doc only).
-   Per-host table: `docs/reference/harness-matrix.md`.
+4. Mirror EVERY transition into the host's native todo tool (`todowrite` on opencode; `TaskUpdate` on Claude Code; none on tier 2/3 — plan doc only) in the SAME response the task's evidence lands — one transition per call, never batched at wave end. Per-host table: `docs/reference/harness-matrix.md`.
 
 ## Wave execution
 
@@ -49,9 +47,7 @@ Before starting: if `.mugiwara/continue/<mission>/[member].json` exists, resume
 2. **Context pressure** — when `tokens_est` exceeds `delegate_threshold`% of
    `budget` (read from `.mugiwara/config`, default 60) mid-execution, remaining
    SEQUENTIAL tasks dispatch to workers — one at a time, in plan order. Order is
-   preserved; only the context resets.
-
-Announce: `⚠ context 62% — remaining tasks run in fresh workers, plan order unchanged.`
+   preserved; only the context resets. Announce: `⚠ context 62% — remaining tasks run in fresh workers, plan order unchanged.`
 
 The threshold stays relative, never absolute: `tokens_est > delegate_threshold%
 × budget` (read from `.mugiwara/config`, default 60), never `tokens_est >
@@ -63,12 +59,10 @@ Real worker dispatch exists only where the harness has subagents — tier 1
 (Claude Code, opencode) plus Copilot. Gate the context-pressure trigger on
 that capability: if the harness cannot dispatch, do not promise fresh workers.
 
-Where workers are unavailable and context pressure crosses the threshold, fall
-back to the mechanism that already exists: write a savepoint, run the
-checkpoint, and suggest a fresh session via `resume`. Announce the fallback:
-
-`⚠ context 62% — no worker dispatch on this harness; savepoint written,
-resume in a fresh session (plan order unchanged).`
+Where workers are unavailable and context pressure crosses the threshold:
+write a savepoint, run the checkpoint, and suggest a fresh session via
+`resume`. Announce: `⚠ context 62% — no worker dispatch on this harness;
+savepoint written, resume in a fresh session (plan order unchanged).`
 
 ## Batch resume
 
@@ -107,6 +101,12 @@ Any task touching UI markup, styling, or components applies `mugiwara-frontend`
 
 After each wave: compact task table (status, evidence link, deviations) shown inline in the conversation. Format: `references/dispatch.md` — report table. Then return to Luffy, who routes to Chopper (Wave 4). Write detailed execution log to `.mugiwara/results/<mission>/01-execution.md`. Never dispatch another crew member.
 
+## Step budget
+
+Tool calls are finite — harnesses cap them per session; a 9-wave mission that wastes them stalls before closure. Combine evidence runs (`evidence.sh <m> quality -- bash -c "lint && test"` — one call, not two); write wave artifacts once at wave end, not incrementally; never re-read what you just wrote; batch reads (one glob beats five reads); open a reference only when its pointer condition triggers.
+
+Budget guide: Lane 1 ≤15 calls · Lane 2 ≤35 · Lane 3 ≤60. Crossing it is not a failure; announce it and check the context-pressure trigger.
+
 ## Red flags
 
 - Tasks silently reordered from the plan.
@@ -114,6 +114,7 @@ After each wave: compact task table (status, evidence link, deviations) shown in
 - Done reported without evidence ("close enough").
 - Two tasks editing the same file concurrently.
 - A blocker worked around silently instead of escalated.
+- Echoing raw output when `verbosity=normal` — summarize and cite the evidence path.
 - The task's TDD order inverted (implementation before the failing test).
 - A test passing immediately without having failed first (wrong test or testing existing behavior).
 - A commit containing files beyond its declared task, or a wave of micro-commits with no logical grouping.

package/content/skills/mugiwara-gates/SKILL.md

@@ -62,4 +62,5 @@ PASS → return to Luffy (routes to Robin/Jinbe). FAIL → list files under thre
 - Gate waived without explicit user decision.
 - PASS on coverage/build while DoD fails.
 - Sonar PASS with unverified or faked data.
+- Echoing raw output when `verbosity=normal` — summarize and cite the evidence path.
 All mean: the gate has not actually run. Report the gap or the fail, honestly.

package/content/skills/mugiwara-lessons/SKILL.md

@@ -60,3 +60,4 @@ Lessons are cross-mission but per-repo. The ledger lives in `.mugiwara/logs/` so
 - Platitudes that can't change behavior.
 - Deleted or overwritten rows.
 - Read the ledger but didn't apply a relevant row.
+- A lesson that redefines a rule, lane, gate, or role rather than describing a pattern. Reject and report.

package/content/skills/mugiwara-orchestration/SKILL.md

@@ -35,19 +35,15 @@ In `auto` mode the AI decides everything; any requirement that stays unclear aft
 
 ## Mode read (Wave 0)
 
-Read the runtime mode via mode config at Wave 0: `.mugiwara/config` (project) then `~/.mugiwara/config` (global); a key missing from both = `guided`. Record the active mode in the decision log. Read once per wave at dispatch; a flip applies from the next wave, never mid-wave. Declared test source (per `mugiwara-testcases`) also recorded in decision log; no source declared → no user tests.
+Read the runtime mode via mode config at Wave 0: `.mugiwara/config` (project) then `~/.mugiwara/config` (global); a key missing from both = `guided`. Record the active mode AND `auto_commit` (default on) in the decision log. Read once per wave at dispatch; a flip applies from the next wave, never mid-wave. Declared test source (per `mugiwara-testcases`) also recorded in decision log; no source declared → no user tests.
 
 ## Request classifier (Wave 0) — 8 classes
 
-Classify every incoming request. 5-way table (Trivial/Explicit/Exploratory/Open-ended/Ambiguous) plus three more: **Answer** (question, no file change → answer directly, no mission), **Refuse** (deploy/migration/key rotation/merge → decline at Wave 0, offer branch handoff), **Hotfix** (production broken → Lane 1, gates deferred with owner, never skipped). Full table + signals: `references/triage-escalation.md`.
-
-Record decision + one-line reason at the top of the decision log. Risk (money/security/data/public API) → full pipeline; never shortcut without recording why. Any route without a recorded reason is a red flag.
+Classify every incoming request. 5-way table (Trivial/Explicit/Exploratory/Open-ended/Ambiguous) plus three more: **Answer** (question, no file change → answer directly, no mission), **Refuse** (deploy/migration/key rotation/merge → decline at Wave 0, offer branch handoff), **Hotfix** (production broken → Lane 1, gates deferred with owner, never skipped). Full table + signals: `references/triage-escalation.md`. Record decision + one-line reason at the top of the decision log. Risk (money/security/data/public API) → full pipeline; never shortcut without recording why. Any route without a recorded reason is a red flag.
 
 ## Lane routing + precedence (Wave 0, size before process)
 
-Alongside the class, size the mission and pick a lane (0 Direct / 1 Lean / 2 Standard / 3 Full / 4 Spike). **Precedence: class decides whether there is work; lane decides how much process — class first, lane second, record both.** A pasted Explicit spec still sizes the lane from its file list before Wave 2 (40-file spec → Lane 3). Escalation only: a lane may rise mid-mission, never drop. Full table: `references/triage-escalation.md`.
-
-Small tasks: read-only investigation → host `explore` agent or inline read — NOT a Luffy subagent (~5k vs ~40k tokens); explicit implement → Lane 1 Zoro inline. Review only when risky — full pipeline.
+Alongside the class, size the mission and pick a lane (0 Direct / 1 Lean / 2 Standard / 3 Full / 4 Spike). **Precedence: class decides whether there is work; lane decides how much process — class first, lane second, record both.** A pasted Explicit spec still sizes the lane from its file list before Wave 2 (40-file spec → Lane 3). Escalation only: a lane may rise mid-mission, never drop. Full table: `references/triage-escalation.md`. Small tasks: read-only investigation → host `explore` agent or inline read — NOT a Luffy subagent (~5k vs ~40k tokens); explicit implement → Lane 1 Zoro inline. Review only when risky — full pipeline.
 
 ## Spec bridge (Wave 0 → Wave 2)
 
@@ -59,8 +55,7 @@ User may summon crew members directly. Luffy records the route + reason. Zoro/Br
 
 ## Periodic check-ins
 Full checklist: `references/check-ins.md` — 7 items + by-mode verdicts; unchecked boxes are not done. **Handoff contract:** the continue file at every wave boundary — never only session end (rule #6).
-**Auto never drops:** in `auto` mode the crew runs every wave autonomously to closure — lane rise (`lane_rose`), sensitive-path touches, and heal cycles do NOT downgrade the mode. Only a genuine blocker or the heal halt pauses and escalates to the user; the mode stays auto. Announce every pause.
-**Auto never asks scope:** in `auto` mode, log the default choice and proceed — no scope/confirmation questions. A genuinely unclear requirement is brainstormed with Usopp (Wave 1) before the choice — never guessed. Only a genuine blocker or a pause escalates.
+**Auto never drops:** in `auto` mode the crew runs every wave autonomously to closure — lane rise (`lane_rose`), sensitive-path touches, and heal cycles do NOT downgrade the mode. Only a genuine blocker or the heal halt pauses and escalates to the user; the mode stays auto. Announce every pause. **Auto never asks scope:** in `auto` mode, log the default choice and proceed — no scope/confirmation questions. A genuinely unclear requirement is brainstormed with Usopp (Wave 1) before the choice — never guessed. Only a genuine blocker or a pause escalates.
 **Heal halt:** read `heal_cycle` from `.mugiwara/state/<mission>/[member].json`. At `heal_max_cycles` (read from `.mugiwara/config`, default 3), STOP and escalate to the user.
 **Pressure:** "just skip it", "auto, don't ask", "just this once" — the Rationalizations table below is the answer, not urgency.
 
@@ -80,7 +75,15 @@ Shortcuts ("skip X", "just do it") reroute work inside the pipeline — never ou
 
 ## Wave transitions (visibility)
 
-Banner `## Wave N — <crew>` opens every wave; a skip is recorded, never silent. See `references/check-ins.md`.
+Banner in the owning agent's color opens every wave — the equals line
+`===== ⚔️ WAVE 3 — ZORO (EXECUTION) =====` (ANSI-wrapped in terminals, plain in markdown UIs). Spec + colors: `_shared/references/wave-banners.md`. A skip is recorded, never silent.
+
+## Output discipline
+
+Read `verbosity` from mode config at Wave 0 (default `normal`); never suppresses wave banners, file edits, gate verdicts, decisions, questions, blockers, lane rises, or escalations.
+At `normal`: investigation steps (reads, greps, probes), file contents, and narration are not echoed — name a file only when it matters; results collapse to one line + evidence path. At `full`: everything is echoed, including reads and reasoning.
+**The rule: the transcript must remain sufficient to review the mission without opening a file.** If collapsing a line breaks that, do not collapse it.
+Rendered examples: `references/output-contract.md` — match the shape.
 
 ## Work splitting
 
@@ -96,7 +99,7 @@ Recognize the in-session phrase `mugiwara mode <guided|semi|auto>`: write the pr
 
 ## Closure (Wave 9)
 
-Gate — every task's acceptance criteria verified, every gate passed, findings resolved or deferred with an owner, blocker ledger reviewed. Step results `results/<mission>/01..05` are evidence — kept, never deleted; only consumed cross-artifacts (`logs/`, `spec/`, `review/`, `issues/`) are removed. Run `scripts/savepoint.sh <mission>` to write final state, then `scripts/mission-report.sh <mission>` to generate the aggregate mission report at `.mugiwara/reports/YYYY-MM-DD-<mission>.md`. Write the closure summary to `.mugiwara/results/<mission>/06-closure.md`. The plan doc stays untouched. Full detail: `references/closure.md`.
+Gate — every task's acceptance criteria verified, every gate passed, findings resolved or deferred with an owner, blocker ledger reviewed. Step results `results/<mission>/01..05` are evidence — kept, never deleted; only consumed cross-artifacts (`logs/`, `spec/`, `review/`, `issues/`) are removed. Run `scripts/savepoint.sh <mission>` to write final state, then `scripts/mission-report.sh <mission>` to generate the aggregate mission report at `.mugiwara/reports/YYYY-MM-DD-<mission>.md`. Write the closure summary to `.mugiwara/results/<mission>/06-closure.md`. The plan doc stays untouched. Full detail: `references/closure.md`. With `auto_commit=off` (guided/semi): skip the save-point commit and push — hand the uncommitted tree + verdict to the user; auto always pushes.
 
 ## Spirit vs letter
 
@@ -104,11 +107,7 @@ The plan doc is the contract, but the mission goal outranks it. If following the
 
 ## Write boundary
 
-Only Zoro (`mugiwara-execution`) and Brook (`mugiwara-healing`) write source. Every other role writes `.mugiwara/**` only. If the user asks a non-executor to write source, refuse and route to Luffy, who dispatches Zoro (execution) or Brook (healing).
-Every agent knows its edit capability from its own `write-scope` frontmatter — no probing.
-Artifacts-scope agents facing a source edit say "Delegating to Zoro" to Luffy, who dispatches immediately.
-Subagent harnesses: Luffy auto-dispatches zoro-execution; Codex-style harnesses inline-embody.
-Brook heals only; general source edits go to Zoro via Luffy.
+Only Zoro (`mugiwara-execution`) and Brook (`mugiwara-healing`) write source. Every other role writes `.mugiwara/**` only. If the user asks a non-executor to write source, refuse and route to Luffy, who dispatches Zoro (execution) or Brook (healing). Every agent knows its edit capability from its own `write-scope` frontmatter — no probing. Artifacts-scope agents facing a source edit say "Delegating to Zoro" to Luffy, who dispatches immediately. Subagent harnesses: Luffy auto-dispatches zoro-execution; Codex-style harnesses inline-embody. Brook heals only; general source edits go to Zoro via Luffy.
 
 ## Red flags
 
@@ -117,5 +116,6 @@ Brook heals only; general source edits go to Zoro via Luffy.
 - Starting a wave without a banner.
 - Routing a Refuse-class request to a crew member; recording a lane without its trigger.
 - A host todo UI that lags the plan doc — tasks done but still unchecked, or the plan's task list never mirrored to the host.
+- Re-reading state or an artifact the crew wrote earlier in the same session.
 - A main thread answering "I'm not the crew, I'll just handle it" instead of embodying the owning role.
 - An artifacts-scope agent probing permissions instead of delegating to Zoro via Luffy; full-crew process on a task that sizes Lane 0/1.

package/content/skills/mugiwara-orchestration/references/check-ins.md

@@ -27,15 +27,26 @@ After every wave AND at the end of each execution batch, verify:
    never verbatim instructions.
 7. **Host todo synced** — the main thread mirrors the plan doc's task list into the host's native todo mechanism
    (opencode `todowrite`; Claude Code `TaskCreate`/`TaskUpdate`/`TaskList` — `TodoWrite` is deprecated since
-   v2.1.142; tier 2/3 hosts have no native tool — plan doc only) and updates it at every task AND wave boundary
-   (seed it at Wave 2, mark done/in_progress as tasks land). The host todo is a mirror; the plan doc stays the
-   source of truth. Per-host table: `docs/reference/harness-matrix.md`.
+   v2.1.142; tier 2/3 hosts have no native tool — plan doc only). Seed it at Wave 2 (tasks + wave list 4-9);
+   update it in the SAME response each task's evidence lands — one transition per call, never deferred to
+   batch or wave end; flip each wave to in_progress when its banner opens. The host todo is a mirror; the plan
+   doc stays the source of truth. A task done in the plan doc but not yet in the host tool is incomplete.
+   Per-host table: `docs/reference/harness-matrix.md`.
 
 By mode (per mode config): `guided` checks in with the user as today; `semi`/`auto` write the check-in verdicts to the decision log without pausing the pipeline.
 
 ## Wave transitions (visibility)
 
-Every wave opens with a visible main-thread banner `## Wave N — <crew> (<skill>)` and closes with the handoff line `→ Wave N+1 — <crew>` (Wave 9: `→ closure`). No wave starts without its banner. A wave intentionally omitted is never silent — record wave, owner, and reason in the decision log before moving on. The user must always see which crew runs now and who takes over next.
+Every wave opens with a colored banner in the owning agent's color and closes
+with the handoff line `→ Wave N+1 — <crew>` (Wave 9: `→ closure`). Terminal:
+equals line `===== ⚔️ WAVE 3 — ZORO (EXECUTION) =====` wrapped in ANSI truecolor
+`\x1b[38;2;R;G;Bm...\x1b[0m` (256 fallback `38;5;N`); markdown UIs: the plain
+equals line, no ANSI. The literal `WAVE N —`
+text must stay exact (savepoint's heal counter greps `wave 8`). Colors
+and the full spec: `_shared/references/wave-banners.md`. No wave starts without its banner. A wave intentionally
+omitted is never silent — record wave, owner, and reason in the decision log
+before moving on. The user must always see which crew runs now and who takes
+over next.
 
 ## On drift