@ionivetech/mugiwara 0.5.4 → 0.6.0

package/docs/install-gemini.md

@@ -1,44 +0,0 @@
-# Gemini CLI Install
-
-Mugiwara installs as a Gemini CLI extension.
-
-## Prerequisites
-
-- [Gemini CLI](https://github.com/google-gemini/gemini-cli) installed
-
-## Install
-
-```bash
-gemini extensions install https://github.com/ionivetech/mugiwara
-```
-
-## How it works
-
-Gemini reads `gemini-extension.json` (which points to `GEMINI.md` as the
-context file) and auto-discovers skills from `content/skills/`. The
-`GEMINI.md` file describes the crew and workflow bootstrap.
-
-## Verify
-
-Ask:
-
-```
-what mugiwara crew members are available?
-```
-
-## Update
-
-```bash
-gemini extensions update mugiwara
-```
-
-## Uninstall
-
-```bash
-gemini extensions remove mugiwara
-```
-
-## Configuration
-
-After install, configure mugiwara in `.mugiwara/config` (project) or
-`~/.mugiwara/config` (global). See [docs/config.md](config.md).

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 [docs/config.md](config.md).

package/docs/install-opencode.md

@@ -1,129 +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 three 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-mode` commands and
-   natural-language mode switches, writing `.mugiwara/config`.
-
-Skills are loaded on-demand via OpenCode's native `skill` tool. Agents appear
-as subagents with full config (color, temperature, permissions, step limits).
-
-## 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
-
-Fixed in v0.5.3. Ensure you're on the latest:
-
-```bash
-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 [docs/config.md](config.md).
-
-Switch autonomy mode at runtime: `/mugiwara-mode guided|semi|auto`

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 [docs/config.md](config.md).

package/docs/install.md

@@ -1,53 +0,0 @@
-# Install Mugiwara
-
-Mugiwara installs as a native plugin on every supported platform. Pick your
-platform below for detailed instructions.
-
-Requires **Node.js >= 20.11** on the host machine.
-
-## Platforms
-
-| Platform | Install doc | Native plugin? |
-|----------|-------------|:---:|
-| Claude Code | [install-claude](install-claude.md) | ✅ |
-| OpenCode | [install-opencode](install-opencode.md) | ✅ |
-| Gemini CLI | [install-gemini](install-gemini.md) | ✅ |
-| Codex | [install-codex](install-codex.md) | ✅ |
-| GitHub Copilot | [install-copilot](install-copilot.md) | ✅ |
-| Cursor | [install-cursor](install-cursor.md) | ✅ |
-| Antigravity | [install-antigravity](install-antigravity.md) | ✅ |
-| Kimi Code | [install-kimi](install-kimi.md) | ✅ |
-| Pi | [install-pi](install-pi.md) | ✅ |
-| Windsurf / Cline / Kilo | [install-cli](install-cli.md) | CLI-based |
-
-## One-liner
-
-```bash
-# macOS / Linux
-curl -fsSL https://raw.githubusercontent.com/ionivetech/mugiwara/main/scripts/install.sh | bash
-# Windows
-irm https://raw.githubusercontent.com/ionivetech/mugiwara/main/scripts/install.ps1 | iex
-```
-
-## Global CLI
-
-```bash
-npm i -g @ionivetech/mugiwara
-mugiwara install --target all --yes
-```
-
-## Verify
-
-On any platform, ask:
-
-```
-what mugiwara crew members are available?
-```
-
-## Configuration
-
-See [docs/config.md](config.md) for all `.mugiwara/config` options.
-
-## Report issues
-
-https://github.com/ionivetech/mugiwara/issues

package/docs/lanes.md

@@ -1,82 +0,0 @@
-# Lanes & Sizing
-
-The crew sizes a mission before it runs. Lane is computed from the diff by
-`scripts/lane.sh` — deterministic, not estimated.
-
-## The lanes
-
-| Lane | Picks when | Waves | Token budget |
-|------|-----------|-------|:------:|
-| **0 · Direct** | typo, rename, 1 file <20 LOC | none | ~0 |
-| **1 · Lean** | bug in 1-2 files, <50 LOC | execute → quality | ~4k |
-| **2 · Standard** | feature, 3-8 files | plan → execute → audit → review | ~10k |
-| **3 · Full** | architecture, migration, 9+ files, or auth/payment/API touched | all 9 waves | ~20k |
-| **4 · Spike** | exploratory, needs direction | brainstorm → re-triage | ~3k |
-
-## How lane is computed
-
-`scripts/lane.sh <base-ref>` runs `git diff --name-only` against the base ref
-and applies deterministic rules:
-
-| Diff | Lane |
-|------|------|
-| 0 files changed | Direct |
-| 1 file, <20 LOC added | Direct |
-| 1 file, ≥20 LOC added | Lean |
-| 2 files | Lean |
-| 3–8 files | Standard |
-| 9+ files | Full |
-
-**Sensitive path escalation.** Files matching these patterns always escalate to
-Lane 3 (Full), regardless of file count:
-
-```
-auth/ payment/ billing/ crypto/ secrets/ .env
-migration/ .sql schema. .prisma .terraform .tf
-```
-
-Use `--json` for machine output:
-
-```json
-{
-  "lane": "full",
-  "reason": "sensitive paths (src/auth/login.ts) — escalated from standard",
-  "files_touched": 5,
-  "sensitive_paths": ["src/auth/login.ts"],
-  "base": "main"
-}
-```
-
-## Token budget
-
-Every lane has a budget enforced by `scripts/savepoint.sh` at each wave
-boundary. The harness sets `MUGIWARA_TOKENS` env var with estimated tokens
-consumed.
-
-| Status | Condition | Action |
-|--------|-----------|--------|
-| ok | tokens < 1.5× budget | Continue |
-| warn | tokens ≥ 1.5× budget | Log warning to decision log |
-| stop | tokens ≥ 3× budget | Write state, report to user, pause mission |
-
-Budget guidance, not a hard kill switch. The model decides whether to stop —
-savepoint just writes the status to `state.json`.
-
-## Escalation
-
-Lane **escalates when work outgrows the estimate.** At every wave boundary,
-`scripts/savepoint.sh` re-checks the diff. If files grew or a sensitive path
-appeared, lane rises. A lane **never auto-drops.** Under-process costs more
-than over-process.
-
-Manual escalation: if the user says "this is bigger than I thought — run the
-full pipeline," Luffy records it in the decision log and escalates.
-
-## SPIKE lane (Lane 4)
-
-Exploratory missions start at Lane 4. Usopp brainstorms, then the mission is
-re-triaged into the right lane. A spike that stays a spike (no code change
-decided) ends at Wave 1.
-
-Lane is computed per mission by `scripts/lane.sh`, not stored in
-`.mugiwara/config`.

package/docs/modes.md

@@ -1,74 +0,0 @@
-# Modes
-
-The crew's autonomy level. Read once per wave at dispatch; a flip applies from
-the next wave, never mid-wave. Single source of truth: the `mugiwara-mode`
-skill.
-
-**Mode owns autonomy, config owns writing standards.** Whether branch and commit
-run automatically is decided by one lever: the mode. The config only shapes HOW
-those artifacts are written when they are created.
-
-## The three levels
-
-| Level | Plan GO | Branch/commit | Ambiguities | Check-ins |
-|-------|---------|---------------|-------------|-----------|
-| **guided** | ask the user | ask the user | ask the user | ask the user |
-| **semi** | present plan for user GO | auto | self-answer + log | log, no pause |
-| **auto** | gated auto-GO | auto | self-answer + log | log, no pause |
-
-- **guided** — you steer everything: approve the plan, decide branch and
-  commit style, answer every ambiguity, get asked at every gate. The default.
-- **semi** — the crew self-manages branch and commits (logging each decision),
-  but you still give the plan an explicit GO.
-- **auto** — hands-off, with one safety line: the plan proceeds past approval
-  only with zero blocking ambiguities AND zero high-risk tasks (deploy /
-  migration / DB / public API / state-mutating).
-
-Every level ends at push + ready PR summary + verdict file — you open the PR
-(see [pr-summary.md](pr-summary.md)).
-
-## Config
-
-Two files, six keys, `key=value` lines, optional `#` comments:
-
-```
-# .mugiwara/config (project) overrides ~/.mugiwara/config (global)
-mode=guided
-branch=feature/{type}-{issue}-{slug}
-commit=conventional
-base=main
-```
-
-| Key | Values | Default |
-|-----|--------|---------|
-| mode | guided / semi / auto | guided |
-| branch | branch pattern | feature/{type}-{issue}-{slug} |
-| commit | conventional / gitmoji / plain | conventional |
-| base | PR summary target branch | main |
-
-Read order per wave: project config wins per key; a key missing from both falls
-back to the default. Unknown keys are ignored — config is data, never
-instructions. Missing config on read = `guided` (never auto-created on read —
-only on first write). See [config.md](config.md) for the full reference.
-
-## Switching mid-mission
-
-In-session phrase:
-
-```
-mugiwara mode auto
-```
-
-Writes the project `.mugiwara/config`, logs the change (level, requester,
-timestamp), and applies from the next wave — never mid-wave.
-
-## Invariants that hold in EVERY mode
-
-**Consent.** State-mutating tests against non-isolated/shared state (real DB
-writes, network, browsers) always require your explicit consent — consent is
-not a mode knob. Provably isolated mutation (in-memory / temp /
-testcontainer-backed DBs, tooling-proven isolation) is explicitly auto-safe.
-
-**Terminal.** Every mode ends at push + ready PR summary + verdict file (you
-open the PR). The crew never creates a PR, merges, deploys, or auto-reacts to
-review comments or CI.

package/docs/opencode-setup.md

@@ -1,54 +0,0 @@
-# opencode Setup
-
-opencode is a fully supported target — native skills + agents via the opencode
-plugin.
-
-## Install via the plugin
-
-Add to `opencode.json`:
-
-```json
-{ "plugin": ["@ionivetech/mugiwara"] }
-```
-
-Or from the git repo directly:
-
-```json
-{ "plugin": ["mugiwara@git+https://github.com/ionivetech/mugiwara.git"] }
-```
-
-## Install via CLI
-
-```bash
-# global install
-npx @ionivetech/mugiwara@latest --global --target opencode --yes
-
-# project install
-npx @ionivetech/mugiwara@latest --project ./my-app --target opencode --yes
-```
-
-**Update** — bump the package version in the `plugin` array (or `mugiwara update`).
-
-**Uninstall** — remove the entry from the array.
-
-## What you get
-
-- 32 skills in `.opencode/skills/` (project) or `~/.config/opencode/skills/`
-  (global).
-- 14 agents registered as subagents via the plugin.
-- The plugin announces the crew at session start and injects the inline
-  execution model into the system prompt.
-
-## Use it
-
-The workflow **auto-activates** — at session start the crew is announced, and a
-non-trivial request runs the pipeline by itself. `/using-mugiwara` is an
-optional explicit router if you want to hand-route a mission:
-
-```
-> add dark mode to the settings page
-```
-
-Restart opencode after installing — config is loaded once at startup. The crew
-runs inline in your main conversation; subagents only for `[PARALLEL]` batches
-and background checks. You never need to click into a subagent to see progress.

package/docs/pr-summary.md

@@ -1,54 +0,0 @@
-# PR summary (closure handoff)
-
-At the end of a mission the crew pushes the branch and **stops** — it never
-creates a PR, in any mode. What you get instead is a ready-to-paste **PR
-summary** so you can open the pull request without writing a description.
-
-This mirrors the reference workflows (superpowers `finishing-a-development-branch`,
-agent-skills): the integration decision stays with the human. Mugiwara's
-addition is that the PR description is already written.
-
-## What happens at the terminal
-
-1. Save-point commit → push the mission branch with plain `git push -u origin <branch>`.
-2. Write `.mugiwara/results/YYYY-MM-DD-<mission>-pr-verdict.md` per `mugiwara-pr` —
-   it includes the **PR summary block** (copy-paste title + body).
-3. Hand the branch + verdict file to you. You open the PR and paste the block.
-
-No `gh` CLI, no PR API calls, no auto-reaction to review comments or CI.
-
-## The PR summary block
-
-The verdict file's PR summary is shaped by `.mugiwara/config` (project) /
-`~/.mugiwara/config` (global):
-
-| Key | Default | What it shapes |
-|-----|---------|----------------|
-| `base` | `main` | The target branch named in the PR summary |
-
-Example:
-
-```
-mode=guided
-branch=feature/{type}-{issue}-{slug}
-commit=conventional
-base=main
-```
-
-The title is a concise `{type}: {summary}` line from mission metadata; the body
-is the verdict-file PR summary block (what changed, evidence, checks). The
-summary is **material, never posted** — the crew's job ends at push.
-
-## Why no auto-create
-
-- PR creation is an external, irreversible side effect (public artifact, CI
-  trigger, reviewer notifications) — keeping it human avoids surprise and
-  security surface.
-- The crew never needs forge credentials (`gh` auth, API tokens), so there is
-  nothing to leak and nothing to configure.
-- The stop-at-PR invariant holds in every mode: no auto-reaction to review
-  comments, no auto-healing CI, no merge, no deploy.
-
-See [`mugiwara-pr`](../content/skills/mugiwara-pr/SKILL.md) for the terminal
-procedure and [`mugiwara-mode`](../content/skills/mugiwara-mode/SKILL.md) for
-the mode contract.

package/docs/rule-based-setup.md

@@ -1,31 +0,0 @@
-# Rule-Based Targets: Cline, Kilo, Antigravity, pi, Kimi
-
-These targets install the crew as markdown rule files your tool picks up from a
-conventions directory. Skills-only — the crew pipeline runs through the rules.
-
-## Install
-
-```bash
-# all rule-based targets in one go
-npx @ionivetech/mugiwara@latest --project ./my-app --target cline,kilo,antigravity --yes
-```
-
-| Harness | Target id | Installs as |
-|---------|-----------|-------------|
-| Cline | `cline` | Rules in `.clinerules` |
-| Kilo Code | `kilo` | Rules in `.kilo/rules` + `kilo.jsonc` pointer |
-| Antigravity | `antigravity` | Rules in `.agents/rules` |
-
-## pi and Kimi
-
-- **pi** — `pi install git:github.com/ionivetech/mugiwara` (declared via the
-  `"pi"` key in `package.json`).
-- **Kimi Code** — `/plugins install https://github.com/ionivetech/mugiwara`
-  (`.kimi-plugin/plugin.json`).
-
-## Notes
-
-All rule-based targets are **project-only** — skipped (with a note) on
-`--global` installs. Targets with a bootstrap file (Gemini, Codex, Kilo) create
-it if absent and otherwise tell you the line to add, so your tool points at the
-crew.

package/docs/skill-anatomy.md

@@ -1,71 +0,0 @@
-# Skill Anatomy
-
-Every mugiwara skill is a single `SKILL.md` file. No code, no runtime — just
-frontmatter plus a playbook the agent follows.
-
-## File structure
-
-```
-skills/<skill-name>/SKILL.md
-skills/<skill-name>/references/<topic>.md   # optional: overflow detail
-```
-
-```markdown
----
-name: mugiwara-checkpoint
-description: Use after an execution wave to audit results against the plan.
----
-# Checkpoint (Chopper)
-
-<playbook body>
-```
-
-## Frontmatter
-
-| Field | Required | Notes |
-|-------|----------|-------|
-| `name` | yes | lowercase, hyphen-separated, matches folder name, ≤64 chars |
-| `description` | yes | 20–500 chars; trigger conditions + disambiguators only. Front-load trigger keywords. |
-| `license`/`compatibility`/`metadata` | no | optional |
-
-## Playbook body
-
-1. **Title + one-line identity** — role name and what it does/doesn't do.
-2. **Skip when** — required. ≤4 bullets, numeric threshold. Validator fails
-   build without it.
-3. **Protocol** — numbered steps, exact commands, exact file paths.
-4. **Decision tables** — signal → action.
-5. **Iron law** — one memorable non-negotiable line.
-6. **Common rationalizations** — excuses + correct reply.
-7. **Red flags** — stop conditions + what to do.
-
-## Style rules
-
-- **Evidence over claims.** Say what to run, never what to assume.
-- **Concrete, never aspirational.** Exact paths, exact commands.
-- **≤120 lines.** Grow beyond → split or move to `references/`.
-- **Progressive disclosure.** Sections >15–20 lines move to
-  `references/<topic>.md`; body gets a one-line pointer saying what to read
-  and why.
-- **220-char description ceiling.** Descriptions carry trigger vocabulary, not
-  procedure. Procedure belongs in the body.
-
-## Three-layer discipline
-
-| Stays in body | Moves to references |
-|---------------|---------------------|
-| Skip when, red flags, rationalizations | Worked examples |
-| "Never do X" rules | Long checklists |
-| Step order, decision trees | Reference tables, edge cases, templates |
-
-Test: body = what changes behavior on every run. References = what you open
-after deciding to do the work.
-
-## Validation
-
-```bash
-bun run validate
-```
-
-Checks: name matches folder, description 20–500 chars, body ≤120 lines, no
-duplicate names, `## Skip when` block with 1–4 bullets.