@ionivetech/mugiwara 0.5.5 → 0.6.1

package/docs/install/kimi.md

@@ -1,45 +0,0 @@
-# Kimi Code Install
-
-Mugiwara installs through Kimi Code's plugin system.
-
-## Prerequisites
-
-- [Kimi Code](https://kimi.moonshot.cn) installed
-
-## Install
-
-```
-/plugins install https://github.com/ionivetech/mugiwara
-```
-
-## How it works
-
-Kimi Code reads `.kimi-plugin/plugin.json` and auto-discovers skills from
-`content/skills/`.
-
-## Verify
-
-Ask:
-
-```
-what mugiwara crew members are available?
-```
-
-## Update
-
-Reinstall:
-
-```
-/plugins install https://github.com/ionivetech/mugiwara
-```
-
-## Uninstall
-
-```
-/plugins remove mugiwara
-```
-
-## Configuration
-
-After install, configure mugiwara in `.mugiwara/config` (project) or
-`~/.mugiwara/config` (global). See [config.md](../concepts/config.md).

package/docs/install/opencode.md

@@ -1,143 +0,0 @@
-# OpenCode Install
-
-Mugiwara installs through OpenCode's native npm plugin system.
-
-## Prerequisites
-
-- [OpenCode](https://opencode.ai) installed
-- Node.js >= 20.11
-
-## Install
-
-Add to `opencode.json` (global at `~/.config/opencode/opencode.json` or
-project-level at `.opencode/opencode.json`):
-
-```json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "plugin": ["@ionivetech/mugiwara"]
-}
-```
-
-Restart OpenCode.
-
-### Pinning a version
-
-```json
-{ "plugin": ["@ionivetech/mugiwara@^0.5.0"] }
-```
-
-## How it works
-
-The plugin (`mugiwara.mjs`) does four things:
-
-1. **Config hook** — registers `content/skills/` as a skills path and
-   `content/agents/` as agents so OpenCode discovers the full crew
-   (26 skills + 14 agents) without any file copying.
-
-2. **System transform hook** — injects the crew announce header and active
-   autonomy mode into every session's system prompt.
-
-3. **Chat message hook** — intercepts `/mugiwara` commands and
-   natural-language mode switches, writing `.mugiwara/config`.
-
-4. **Commands** — the file-based installer copies slash commands
-   (`/mugiwara`, `/using-mugiwara`, `/mugiwara-plan`, etc.) to
-   `.opencode/commands/`.
-
-Skills are loaded on-demand via OpenCode's native `skill` tool. Agents appear
-as subagents with full config (color, temperature, permissions, step limits).
-
-## Mode switching
-
-Switch autonomy mode at runtime:
-
-```
-/mugiwara guided    # human decides every GO
-/mugiwara semi      # auto branch + commit, plan needs GO
-/mugiwara auto      # hands-off except high-risk
-/mugiwara           # show current mode
-```
-
-## Verify
-
-Ask your agent:
-
-```
-what mugiwara crew members are available?
-```
-
-Or type `/mugiwara` to see the crew router.
-
-## Update
-
-```bash
-npm update @ionivetech/mugiwara
-```
-
-Or bump the version constraint in `opencode.json` and restart.
-
-## Uninstall
-
-Remove `"@ionivetech/mugiwara"` from the `plugin` array in `opencode.json`,
-then restart OpenCode.
-
-## Troubleshooting
-
-### Plugin not loading
-
-1. Check logs: `opencode --print-logs`
-2. Verify the plugin line in `opencode.json`
-3. Ensure you're on a recent OpenCode version
-
-### Server error on startup
-
-Clear stale plugin cache and reinstall:
-
-```bash
-rm -rf ~/.cache/opencode/packages/@ionivetech
-npm update @ionivetech/mugiwara
-```
-
-If it persists, file at https://github.com/ionivetech/mugiwara/issues.
-
-### Skills not found
-
-1. Use the `skill` tool to list available skills
-2. Check the plugin loaded (see "Plugin not loading")
-3. Each skill needs a `SKILL.md` with valid YAML frontmatter (`name`, `description`)
-
-### Windows
-
-Some Windows OpenCode builds have Bun path issues with npm packages. If the
-plugin won't install, try:
-
-```powershell
-npm install @ionivetech/mugiwara --prefix "$HOME\.config\opencode"
-```
-
-Then use the local path in `opencode.json`:
-
-```json
-{ "plugin": ["~/.config/opencode/node_modules/@ionivetech/mugiwara"] }
-```
-
-## Tool mapping
-
-Mugiwara skills reference general actions. On OpenCode these map to:
-
-| Action | OpenCode tool |
-|--------|---------------|
-| Create a todo | `todowrite` |
-| Dispatch a subagent | `task` with `subagent_type` |
-| Invoke a skill | `skill` |
-| Read a file | `read` |
-| Edit a file | `edit` or `write` |
-| Run a shell command | `bash` |
-| Search code | `grep`, `glob` |
-| Fetch a URL | `webfetch` |
-
-## Configuration
-
-After install, configure mugiwara in `.mugiwara/config` (project) or
-`~/.mugiwara/config` (global). See [config.md](../concepts/config.md).

package/docs/install/pi.md

@@ -1,46 +0,0 @@
-# Pi Install
-
-Mugiwara installs as a Pi package.
-
-## Prerequisites
-
-- [Pi](https://github.com/pi) CLI installed
-
-## Install
-
-```bash
-pi install git:github.com/ionivetech/mugiwara
-```
-
-## How it works
-
-Pi reads `package.json` `pi` field (`skills: ["./content/skills"]`) and
-loads all 26 skills. The Pi extension (`pi-extension/`) registers runtime
-hooks if present.
-
-## Verify
-
-Ask:
-
-```
-what mugiwara crew members are available?
-```
-
-## Update
-
-Reinstall with the same command:
-
-```bash
-pi install git:github.com/ionivetech/mugiwara
-```
-
-## Uninstall
-
-```bash
-pi remove mugiwara
-```
-
-## Configuration
-
-After install, configure mugiwara in `.mugiwara/config` (project) or
-`~/.mugiwara/config` (global). See [config.md](../concepts/config.md).

package/docs/reference/adoption-guide.md

@@ -1,72 +0,0 @@
-# Adoption Guide
-
-How to take the crew into your workflow without fighting it.
-
-## Pick your harness
-
-The crew ships native skills + agents where the harness supports them, and
-markdown rule files everywhere else.
-
-| Situation | Pick |
-|-----------|------|
-| You live in Claude Code or opencode | Native install — agents + skills + (Claude) session hook |
-| You want the full crew pipeline | Claude Code, opencode |
-| You want skills-only, any tool | `npx skills add ionivetech/mugiwara` (agentskills.io layout) |
-| You only use one niche tool | Its per-harness guide (index → install by harness) |
-
-Native targets (Claude Code, opencode, Copilot) register the 14 agents directly.
-Rule-based targets (Gemini, Codex, Cursor, Windsurf, Cline, Kilo, Antigravity)
-get the same 32 skills as markdown rules plus a bootstrap pointer, so the crew
-is still steered even where subagents don't exist.
-
-## Pick your mode
-
-Modes live in `.mugiwara/config` (project) or `~/.mugiwara/config` (global):
-
-```
-mode=guided
-branch=feature/{type}-{issue}-{slug}
-commit=conventional
-```
-
-| Level | What it asks you |
-|-------|------------------|
-| `guided` | Plan GO, branch, commits, ambiguities, check-ins — everything |
-| `semi` | Plan GO only; branch/commits/ambiguities self-answer and log |
-| `auto` | Nothing, unless a high-risk task exists (auto-GO is gated) |
-
-State-mutating tests against shared state (real DB writes, network, browsers)
-always need your explicit consent — in every mode. That consent is not a knob.
-
-Missing config on read = `guided`. A flip applies from the next wave, never
-mid-wave.
-
-## Fit the crew to your workflow
-
-- **Trivial one-liners** don't need the crew's full pipeline — Luffy routes them
-  to Lane 0 and they run with zero waves. The process scales to the work.
-- **Medium features** run the standard pipeline: triage → plan → execute →
-  checkpoint → quality → gates → review → closure.
-- **High-stakes work** (money, security, data, public API) always gets the full
-  pipeline, including Skeptic's adversarial pass and Brook's heal loop.
-- **Repos the crew has touched before** read the lessons ledger at triage, so
-  every mission stands on the previous ones.
-
-## The execution model, in one sentence
-
-The crew runs **inline in your main conversation**; subagents are used only for
-independent `[PARALLEL]` task batches and background checks. You see every wave
-as it happens. See [execution-model.md](../concepts/execution-model.md).
-
-## What the crew will never do
-
-- Merge a PR, or deploy. It pushes the branch and hands you the verdict file —
-  PR review is the terminal gate.
-- Auto-react to review comments or CI.
-- Let a wave pass on a spoken claim — evidence or it didn't happen.
-- Work around a blocker silently — everything lands in the ledger.
-
-## Going further
-
-- [Developer onboarding](developer-onboarding.md) if you want to contribute.
-- [Comparison](../concepts/comparison.md) if you're weighing mugiwara against alternatives.

package/docs/reference/agent-anatomy.md

@@ -1,72 +0,0 @@
-# Agent Anatomy
-
-Every mugiwara agent is a portable markdown file that names a crew member's
-persona, rules, and output contract. Agents are harness-native where supported
-(Claude Code, opencode) and markdown rule files elsewhere.
-
-## File structure
-
-```
-agents/<name>.md
-```
-
-```markdown
----
-name: chopper-checkpoint
-description: Dispatch after each execution wave to audit results against the plan - re-runs every acceptance criterion, verifies commit hygiene and parallel-file safety, classifies failures honestly, appends ledger rows, and issues a Definition-of-Done verdict. Auditor only; never fixes code.
-skills: mugiwara-checkpoint
----
-
-# Chopper — Checkpoint (Auditor)
-
-## Role
-...
-```
-
-## Frontmatter
-
-| Field | Required | Notes |
-|-------|----------|-------|
-| `name` | yes | lowercase, hyphen-separated; matches the file name |
-| `description` | yes | ≥20 chars; what this agent does and when to summon it |
-| `skills` | no | the crew skills this member holds, comma-separated |
-
-Harness-specific agents (opencode) may add `mode`, `permission`, `model`, etc.
-in their own installation copy — the content stays portable.
-
-## The body — house style
-
-Agents follow a fixed skeleton so every member reads the same way:
-
-1. **Role** — one paragraph: what the member does and the boundary it never
-   crosses ("Auditor, not fixer", "never implements code").
-2. **Experience** — a one-line persona so the model adopts the right instincts
-   ("QA lead who has caught 'works on my machine' for 20 years").
-3. **When dispatched** — which wave of `mugiwara-workflow` and with what inputs.
-4. **Rules** — numbered, each an action bound to its reason, deferring to the
-   held skill for the full protocol.
-5. **Output** — where the artifact lands (`.mugiwara/results/...`) and how it
-   routes.
-6. **Red flags** — behaviors that mean the member stopped doing its job.
-
-## Agent vs skill
-
-- A **skill** is the reusable playbook ("how to audit a wave").
-- An **agent** is the persona that applies it ("Chopper is the auditor; Chopper
-  never fixes code").
-
-One agent holds many skills (Zoro holds `mugiwara-execution`, `mugiwara-git`,
-`mugiwara-mode`, `mugiwara-testcases`, `mugiwara-backend`). When the crew runs
-inline, the main thread loads the member's skills and embodies the persona.
-
-## Validation
-
-Agents are validated alongside skills on check-in (name, description length,
-sync between `content/` and the repo-root plugin copies). Run:
-
-```bash
-bun run validate
-bun run validate --check-sync
-```
-
-See [developer-onboarding.md](developer-onboarding.md).

package/docs/reference/compliance-matrix.md

@@ -1,81 +0,0 @@
-# Compliance Matrix
-
-For each model + harness + tier combination, how well mugiwara's rules hold.
-Published with failures — the first pack to admit where it breaks.
-
-## How to read
-
-- ✅ Rule holds ≥90% of the time
-- ⚠️ Rule holds 60-89% of the time — use guided mode, or expect model to miss it
-- ❌ Rule holds <60% of the time — not reliable, document the gap
-
-## Rules under test
-
-| # | Rule | Mechanism | Pillar |
-|---|------|-----------|--------|
-| R1 | Lane sizing | `scripts/lane.sh` | 2 |
-| R2 | Skip gates respected | Skill prose | 1 |
-| R3 | Evidence over claims | Chopper re-verification | 1 |
-| R4 | Wave boundaries (banner + report) | Workflow skill | 2 |
-| R5 | Heal loop bound (≤3 cycles) | Orchestration skill | 2 |
-| R6 | DoD verified (5 axes) | `references/definition-of-done.md` | 1 |
-| R7 | State written at wave boundary | `scripts/savepoint.sh` | 2 |
-| R8 | Source-backed code (no hallucinated APIs) | `references/source-grounding.md` | 4 |
-| R9 | Blocker ledger written on failure | Agent discipline | 1 |
-| R10 | Mission report at closure | `scripts/savepoint.sh` | 1 |
-
-## Results by model
-
-### Claude Sonnet 4 — opencode (Tier 1)
-
-| Rule | Verdict | Notes |
-|------|---------|-------|
-| R1 | ✅ | Lane computed by script |
-| R2 | ⚠️ | Occasionally skips on low-signal tasks |
-| R3 | ✅ | Chopper re-runs checks reliably |
-| R4 | ✅ | Banners + reports consistent |
-| R5 | ✅ | Heal loop bound respected |
-| R6 | ✅ | DoD axes checked |
-| R7 | ✅ | Savepoint script runs |
-| R8 | ⚠️ | Hallucinates APIs ~8% of the time without source-grounding |
-| R9 | ✅ | Ledger entries reliable |
-| R10 | ✅ | Closure report written |
-
-### Gemini — Gemini CLI (Tier 2)
-
-| Rule | Verdict | Notes |
-|------|---------|-------|
-| R1 | ✅ | Lane computed by script |
-| R2 | ⚠️~ | Skip gates respected ~65% |
-| R3 | ⚠️ | Evidence checks sometimes skipped |
-| R4 | ⚠️ | Wave banners inconsistent |
-| R5 | ⚠️ | Heal loop may exceed 3 cycles |
-| R6 | ⚠️ | DoD enforcement weaker |
-| R7 | ✅ | Savepoint script runs |
-| R8 | ❌ | Hallucinated APIs frequent without source-grounding loaded |
-| R9 | ❌ | Blocker ledger often empty even on failures |
-| R10 | ⚠️ | Mission report sometimes incomplete |
-
-### Windsurf — Cline (Tier 3)
-
-| Rule | Verdict | Notes |
-|------|---------|-------|
-| R1 | ✅ | Lane computed by script |
-| R2 | ❌ | Stub-only — model rarely opens refs/ body |
-| R3 | ❌ | Evidence discipline absent without full body loaded |
-| R4 | ❌ | Wave chaining broken without orchestration body |
-| R5 | ❌ | Heal loop unenforced |
-| R6 | ❌ | DoD unverified |
-| R7 | ✅ | Savepoint script runs |
-| R8 | ❌ | No source-grounding without body loaded |
-| R9 | ❌ | No ledger without body loaded |
-| R10 | ✅ | Report generated from state.json |
-
-## Methodology
-
-Foreign-repo validation: same non-trivial task run on ≥10 repos per cell.
-Each rule checked against the expected artifact. Verdict based on pass rate
-across repos, not a single run.
-
-*Last updated: Aug 2026. Results are preliminary — foreign-repo validation
-pending.*

package/docs/reference/developer-onboarding.md

@@ -1,89 +0,0 @@
-# Developer Onboarding
-
-Set up, validate, and contribute to the mugiwara repo.
-
-## Requirements
-
-| Dependency | Required for | Version |
-|------------|--------------|---------|
-| Node.js | running the CLI and the built artifact | >= 20.11 |
-| Bun | building from source, running tests | optional (preferred) |
-
-```bash
-bun install
-```
-
-## Repo layout
-
-```
-mugiwara/
-├── content/            # single source of truth: skills/ + agents/ markdown
-├── agents/             # symlink → content/agents (Claude Code plugin reads plugin root)
-├── skills/             # symlink → content/skills
-├── src/                # CLI, installer, targets, frontmatter parser
-├── scripts/            # validate-content, sync-version, run-evals, install scripts
-├── test/               # vitest suite
-├── .opencode/plugins/  # opencode plugin (registers crew at config load)
-├── .claude-plugin/     # Claude Code marketplace + sync.sh (symlink guard)
-└── docs/               # these docs
-```
-
-## The source of truth
-
-`content/` is the only physical source. The repo-root `agents/` and `skills/`
-are **symlinks** into it, so harnesses that read the plugin root (Claude Code
-marketplace) see the same files — there is no copy to drift. On a fresh clone
-where the symlinks are missing, recreate them:
-
-```bash
-sh .claude-plugin/sync.sh
-```
-
-Always edit `content/`. `bun run validate --check-sync` verifies the symlinks
-resolve to `content/` and never diverge.
-
-## Validation
-
-```bash
-bun run validate                # 26 skills + 14 agents: names, descriptions, skip gates, line limits
-bun run validate --check-sync   # symlinks resolve to content/, never diverge
-bun run typecheck               # tsc --noEmit
-bun run test                    # vitest
-bun run evals                   # eval suite valid (structure + coverage gates)
-bun run evals --run             # optional: execute cases against a model CLI (MUGIWARA_EVAL_CMD)
-```
-
-## Editing a skill or agent
-
-1. Edit `content/skills/<name>/SKILL.md` or `content/agents/<name>.md`.
-2. Respect the house style (see [skill-anatomy.md](skill-anatomy.md) and
-   [agent-anatomy.md](agent-anatomy.md)): evidence over claims, exact commands,
-   red flags, ≤120-line skill bodies.
-3. `bun run validate && bun run typecheck && bun run test`
-
-## Adding a new skill or agent
-
-1. Create the content file following the anatomy docs.
-2. If it's an agent, list its held skills in frontmatter; give it a
-   `description` ≥20 chars.
-3. If it's a skill, pick a folder name that matches `name`; description 20–500
-   chars; body ≤120 lines; include a `## Skip when` block (1–4 bullets, numeric
-   thresholds) so the skill knows when it does not apply.
-4. Update the crew/technique tables in `README.md` and the docs (`agents.md`,
-   `skills.md`).
-5. Sync + validate + test.
-
-## Building and publishing
-
-```bash
-bun run build          # dist/mugiwara.js
-bun run sync-version   # sync version from package.json into manifests
-bun prepack            # build + sync-version
-```
-
-Version numbers in the manifests sync from `package.json` via `sync-version`
-(runs automatically on publish).
-
-## Contributing
-
-Open an issue or pull request on GitHub: <https://github.com/ionivetech/mugiwara>.

package/docs/reference/enforcement.md

@@ -1,35 +0,0 @@
-# Enforcement
-
-A markdown harness cannot force a model to comply with prose — that is the
-ceiling of every skills pack, mugiwara included. What keeps the pipeline honest
-is a mix of mechanism and discipline.
-
-## Mechanisms (computed, no model)
-
-| Rule | Mechanism |
-|------|-----------|
-| Lane sizing | `scripts/lane.sh` computes lane from `git diff --name-only` |
-| State persistence | `scripts/savepoint.sh` writes `state.json` at every wave boundary |
-| Evidence capture | `scripts/evidence.sh <label> -- <cmd>` writes stdout/stderr to `.mugiwara/results/<hash>.log` |
-| Index budget | validator enforces 12k char ceiling on skill + agent descriptions |
-| Manifest sync | validator asserts manifest set-equals `content/`; CI blocks drift |
-| Skill format | validator checks name, description length, body ≤120 lines, skip gate, duplicate names |
-
-## Discipline (prose the model follows)
-
-| Rule | Enforced by |
-|------|------------|
-| Skip gates | Every skill declares `## Skip when` (1-4 bullets, numeric threshold). Validator fails build without it. |
-| Evidence over claims | Iron law in every skill: no wave passes on assertion. Checked by Chopper's re-verification. |
-| Wave boundaries | Every wave opens with `## Wave N — <crew>` banner, closes with checkpoint report. |
-| Heal loop bound | Max 3 cycles (Wave 8 → Wave 4). After 3, escalate to human. |
-| DoD canonical | `references/definition-of-done.md` — one bar, linked from checkpoint + gates. |
-
-## Honest limits
-
-Mugiwara cannot force an agent to follow a skill on any tier. Models can skip
-a skill, rush a wave, or pass on a claim. Mechanisms (savepoint, lane, evidence)
-leave a trace regardless of model cooperation. Discipline rules rely on the
-model reading and choosing to follow them.
-
-That is true on every tier and every harness. Mugiwara is a skills pack, not a supervisor.

package/docs/reference/harness-matrix.md

@@ -1,41 +0,0 @@
-# Harness Matrix
-
-What actually differs per harness tier. Every skill and agent file ships to every harness, but behavior differs in three tiers.
-
-| Tier | Harnesses | Skills | Agents | `references/` | Scope |
-|------|-----------|--------|--------|:---:|-------|
-| **1** | Claude Code, opencode | Native, auto-trigger per skill | Real, dispatchable | Yes | global + project |
-| **2** | Gemini, Codex, Copilot | Full body in rules dir + bootstrap pointer | Markdown only | Yes | project only |
-| **3** | Windsurf, Cline, Kilo, Antigravity | Stub; body in `.mugiwara/refs/` | Stub | Yes | project only |
-
-## Behavioral differences
-
-### Tier 1 — Full
-
-- Skills auto-trigger when `description` frontmatter matches the task.
-- Agents are dispatchable subagents with isolation.
-- Progressive disclosure works: description → body → `references/`.
-- Global scope supported — install once, use in every project.
-
-### Tier 2 — Skills only
-
-- Agent files are markdown — the main thread embodies the persona, no subagent dispatch.
-- Skills load as rules files; the model chooses which to read per task.
-- **Project scope only** — `generic.ts` throws on global scope.
-- `references/` files are copied to `.mugiwara/refs/` and reachable.
-
-### Tier 3 — Stubs
-
-- Rule directories get **stub files** — the frontmatter and a pointer to `.mugiwara/refs/`.
-- Full body is loaded only when the agent opens the reference file.
-- Saves ~40k tokens of glob-load. Trade: the model must decide to open the ref.
-- **Project scope only.**
-- `references/` files are copied to `.mugiwara/refs/` — depth is available, just not auto-loaded.
-- Wave-boundary state flush: savepoint writes `state.json` so the model has computed state to resume from.
-
-## What's the same everywhere
-
-- All 26 skill directories ship to every harness.
-- All 14 agent markdown files ship to every harness.
-- `references/` files are always copied.
-- The workflow, lane sizing, and evidence discipline are identical — the difference is in how the model loads them.