@neikyun/ciel 6.11.3 → 6.13.0

package/assets/commands/ciel-eval.md

@@ -1,50 +1,42 @@
 ---
-description: Runs the binary eval dataset for one or all Ciel skills via claude --print headless, comparing variants.
+description: Runs the binary eval dataset for a Ciel skill via headless Claude Code, comparing baseline scores and persisting results.
 ---
 
-# /ciel-eval — Run eval harness
+# /ciel-eval — Run skill eval harness
 
-*Runs the binary eval dataset for one skill (or all skills) via `claude --print` headless mode, comparing variants and persisting scoreboards.*
+Runs the binary eval dataset for a skill via headless Claude Code, persisting scoreboards to `~/.ciel/evals/results/`.
 
 Usage: `/ciel-eval [skill-name]`
 
-- No arg → runs baseline eval for ALL skills that have a dataset
-- `skill-name` → runs eval for that skill only (baseline + any variants in `variants/`)
+- No arg — runs baseline eval for ALL skills that have a dataset
+- `skill-name` — runs eval for that skill only
 
 ---
 
 ## What it does
 
-1. Dispatches the `improver` agent in MODE=EVAL
-2. The agent invokes `skill-variant-evaluator` skill
-3. For each target skill:
+1. Dispatches `ciel-improver` agent in MODE=EVAL
+2. For each target skill:
    - Loads dataset from `evals/datasets/<skill-name>.jsonl`
-   - If variants exist (`skills/<category>/<name>/variants/*.md`), evaluates each
-   - Otherwise, baseline-only scoring
-4. Persists results to `evals/results/<skill-name>-<timestamp>.json`
-5. Returns a scoreboard
+   - Runs each entry via `claude --print` headless
+   - Scores against expected behaviors
+3. Persists results to `~/.ciel/evals/results/<skill-name>-<timestamp>.json`
+4. Returns a scoreboard
 
 ---
 
 ## Example output
 
 ```
-# Eval results — flux-narrator
+# Eval results — api-design
 
-Dataset: evals/datasets/flux-narration.jsonl (8 entries)
-Variants evaluated: 3
+Dataset: evals/datasets/api-design.jsonl (12 entries)
 
-| Variant | Score | Tokens | Duration |
-|---------|-------|--------|----------|
-| A (baseline) | 0.72 | 14.5k | 12.5s |
-| B (tightened) | 0.89 | 15.1k | 13.2s ← WINNER |
-| C (reduced) | 0.81 | 12.8k | 11.7s |
+Score: 0.85 (25/28 criteria passed)
+Tokens used: 18.2k
+Duration: 15.3s
 
-Winner: **Variant B** (+0.17 over baseline)
-
-Recommendation: adopt Variant B via `/ciel-improve`
-
-Result persisted: evals/results/flux-narrator-2026-04-17-142345.json
+Result persisted: ~/.ciel/evals/results/api-design-2026-05-23-142345.json
 ```
 
 ---
@@ -52,29 +44,25 @@ Result persisted: evals/results/flux-narrator-2026-04-17-142345.json
 ## Guardrails
 
 - **Max 20 eval entries per dataset** — prevents runaway costs
-- **Max 3 variants per skill** — A/B/C, more is noise
-- **Cost estimation** — displayed before starting; user can abort if > 500k tokens projected
-- **Read-only evals** — `--disallowed-tools "Write Edit NotebookEdit"` to prevent side effects
-- **Graceful fallback** — if `claude --print` is unavailable, outputs manual eval prompts and waits for user input
+- **Cost estimation** — displayed before starting; abort if > 500k tokens projected
+- **Read-only**: `--disallowed-tools "Write Edit NotebookEdit"` to prevent side effects
+- **Graceful fallback**: if `claude --print` unavailable, outputs manual eval prompts
 
 ---
 
 ## When to run
 
-- Before and after every `/ciel-improve` pass (baseline vs improved)
-- On every CHANGELOG version bump — regression sanity check
-- When creating a new skill — establish baseline score
-- When adding new eval criteria — re-score existing skills
+- Before and after `/ciel-improve` — baseline vs improved
+- On VERSION bump — regression sanity check
+- When creating a new skill — establish baseline
 
 ---
 
 ## Eval dataset format
 
-One JSON object per line (JSONL). See `evals/datasets/depth-classification.jsonl` for examples. Required fields:
+One JSON object per line (JSONL). Required fields:
 
 - `id` — unique in dataset
 - `input` — prompt / context passed to skill
-- `expected_behavior` — object mapping criterion name → boolean
+- `expected_behavior` — object mapping criterion name to boolean
 - `skill` — which skill this tests
-
-See `skills/meta/skill-variant-evaluator/reference.md` for the full schema and supported criterion evaluators.

package/assets/commands/ciel-init.md

@@ -1,22 +1,20 @@
 ---
-description: Bootstrap or repair Ciel wiring. Auto-detects platform (Claude Code, OpenCode, Cursor, etc.) and configures hooks. Preserves existing config, creates backups.
+description: Bootstrap or repair Ciel v7 wiring. Auto-detects platform (Claude Code or OpenCode) and configures hooks, agents, and commands. Preserves existing config, creates backups.
 ---
 
 # /ciel-init — Wire Ciel into Current Project
 
-**Purpose:** Fix the #1 Ciel failure mode — hooks not firing because config is missing, has wrong paths, or platform not detected.
+**Purpose:** Fix the #1 failure mode — hooks not firing because config is missing or has wrong paths.
 
-**Usage:** `/ciel-init [--check] [--user] [--platform=NAME]`
+**Usage:** `/ciel-init [--check] [--user] [--platform=claude|opencode]`
 
 - `--check` — Dry-run: show what would change without writing
 - `--user` — Install to user scope (~/.claude/settings.json) instead of project
-- `--platform=NAME` — Force platform (claude, opencode, cursor, windsurf, codex, kilocode, ollama, lmstudio)
-
----
+- `--platform=NAME` — Force platform (default: auto-detect)
 
 ## Instructions
 
-You are repairing Ciel wiring. This is deterministic — NO agent dispatch, NO research, NO pipeline.
+This is deterministic — NO agent dispatch, NO research, NO pipeline.
 
 ### Step 1: Detect Platform
 
@@ -25,144 +23,56 @@ Run detection in order (pick FIRST match):
 1. **Project files:**
    - `./opencode.json` or `./.opencode/` → **opencode**
    - `./.claude/settings.json` or `./.claude/` → **claude**
-   - `./.cursor/` → **cursor**
-   - `./.windsurf/` → **windsurf**
-   - `./.codex/` → **codex**
-   - `./.kilocode/` or `./.kilo/` → **kilocode**
 
 2. **CLI availability:**
    - `command -v claude` → **claude**
    - `command -v opencode` → **opencode**
-   - `command -v ollama` → **ollama**
 
 3. **If ambiguous:** Ask user to specify with `--platform=NAME`
 
-### Step 2: Find Ciel Directory
+### Step 2: Find Ciel Source
 
 Check in order:
-1. `$CLAUDE_PLUGIN_DIR/ciel` (if env var set)
-2. `$HOME/.claude/plugins/ciel`
-3. `$HOME/.ciel`
-4. `find "$HOME" -maxdepth 5 -path '*/ciel/hooks/session-start.sh' 2>/dev/null | head -1`
-
-If not found → Tell user to run install first:
-```bash
-bash <(curl -fsSL https://raw.githubusercontent.com/KaosKyun/Ciel/main/scripts/install.sh)
-```
-
-### Step 3: Verify Hooks Exist
-
-Check for 8 required hooks in `$CIEL_DIR/hooks/`:
-```
-session-start.sh, user-prompt-submit.sh, pre-tool-write.sh, post-tool-write.sh,
-stop.sh, subagent-stop.sh, pre-compact.sh, pre-agent-gate.sh
-```
-
-If missing → Copy from nearest Ciel source or tell user to reinstall.
-
-### Step 4: Configure Platform
-
-#### Claude Code Branch
-
-**Config file:** `./.claude/settings.json` (project) or `$HOME/.claude/settings.json` (user)
-
-**Before writing:**
-1. Check CWD sanity — warn if running Claude from different directory
-2. Backup existing config: `cp file.json file.json.bak-TIMESTAMP`
-
-**Write config:**
-```json
-{
-  "hooks": {
-    "SessionStart": { "command": "$CIEL_DIR/hooks/session-start.sh", "stdin": true },
-    "UserPromptSubmit": { "command": "$CIEL_DIR/hooks/user-prompt-submit.sh", "stdin": true },
-    "PreToolUse": { "command": "$CIEL_DIR/hooks/pre-tool-write.sh", "stdin": true, "matcher": "Write|Edit" },
-    "PostToolUse": { "command": "$CIEL_DIR/hooks/post-tool-write.sh", "stdin": true, "matcher": "Write|Edit" },
-    "PreCompact": { "command": "$CIEL_DIR/hooks/pre-compact.sh", "stdin": true },
-    "Stop": { "command": "$CIEL_DIR/hooks/stop.sh", "stdin": true }
-  }
-}
-```
-
-#### OpenCode Branch
-
-**Config file:** `./opencode.json`
-
-**Before writing:**
-1. Backup: `cp opencode.json opencode.json.bak-TIMESTAMP`
-2. Merge existing config (preserve model, provider, mcp, keybinds)
-
-**Ensure:**
+1. `$CLAUDE_PROJECT_DIR/.claude/hooks/` — project-scoped install (v7 default)
+2. `$HOME/.ciel/` — user-level sentinel
+3. If not found → tell user to install:
+   ```bash
+   bash <(curl -fsSL https://raw.githubusercontent.com/KaosKyun/Ciel/main/scripts/install.sh)
+   ```
+
+### Step 3: Configure Platform
+
+**Claude Code** — Backup then write `.claude/settings.json` with hooks registered:
+- SessionStart, UserPromptSubmit, PreToolUse (Edit|Write + Bash rm + Agent), PostToolUse (Edit|Write), SubagentStart (ciel-*), Stop, SubagentStop, PreCompact
+- Copy agents from source to `.claude/agents/`
+- Copy commands from source to `.claude/commands/`
+- Copy skills from source to `.claude/skills/`
+- Ensure `CLAUDE.md` references Ciel pipeline
+
+**OpenCode** — Backup then ensure `opencode.json`:
 - `plugin` array contains `"./.opencode/plugins/ciel.ts"`
 - `instructions` array contains `"AGENTS.md"`
+- Copy plugin, agents, commands to `.opencode/`
 
-**Copy files:**
-- `.opencode/plugins/ciel.ts`
-- `.opencode/agents/ciel-*.md` (6 files)
-- `.opencode/commands/ciel-*.md` (9 files)
-
-#### Other Platforms Branch
+### Step 4: Verify
 
-Install platform-specific artifacts:
-- **Cursor:** `.cursor/rules/ciel.mdc`
-- **Windsurf:** `.windsurf/rules/*.md`
-- **Codex:** `AGENTS.md`, `.codex/hooks.json`
-- **Kilocode:** `.kilocode/rules/ciel.md`, `.kilo/agents/*`
-- **Ollama:** `Modelfile` (user runs `ollama create`)
-- **LM Studio:** `ciel.preset.json`, `system-prompt.md`
+1. Config file exists at expected path
+2. Hooks are executable: `chmod +x .claude/hooks/*.sh`
+3. Agent definitions present (4 files)
+4. Report summary: platform, config path, hooks count, next steps
 
-### Step 5: Verification
+## What's preserved
 
-After configuration, verify:
-
-1. **Config file exists** at expected path
-2. **Hooks are executable:** `chmod +x "$CIEL_DIR/hooks/"*.sh`
-3. **Plugin file syntax valid** (for OpenCode: `npx tsc --noEmit`)
-
-### Step 6: Report
-
-Output summary:
-
-```
-✓ /ciel-init completed
-
-Platform: Claude Code
-Config: /path/to/settings.json
-CIEL_DIR: /path/to/ciel
-Hooks: 8/8 present
-
-Next steps:
-1. Restart Claude Code
-2. Run a test prompt — should see depth hint
-3. Make code changes — should see RELIRE reminder
-```
-
----
+- `ciel-overlay.md` — project-specific rules
+- `.ciel/` — state directory (map.json, memory.json, parking.md)
+- Existing `settings.json` — merged non-destructively
+- Existing `opencode.json` — merged non-destructively
 
 ## Error Handling
 
 | Error | Action |
 |-------|--------|
-| Ciel directory not found | Tell user to run install script |
-| Hooks missing | Try to copy from source, else reinstall |
+| Ciel source not found | Tell user to run install script |
 | Config write fails | Show manual instructions |
 | Platform ambiguous | Ask user to specify with --platform |
-| Permission denied | Suggest running with sudo or check file permissions |
-
----
-
-## Examples
-
-```bash
-# Auto-detect and install to project
-/ciel-init
-
-# Force Claude Code, user scope
-/ciel-init --platform=claude --user
-
-# Check what would change (dry-run)
-/ciel-init --check
-
-# Force OpenCode
-/ciel-init --platform=opencode
-```
+| Permission denied | Check file permissions |

package/assets/commands/ciel-status.md

@@ -1,40 +1,43 @@
 ---
-description: Displays the current Ciel environment status — active version, loaded skills, registered hooks, last session state, and configuration health. A diagnostic entry point for "is Ciel working?" questions.
+description: Displays current Ciel environment status — version, platform, hooks, skills, agents, commands, memory health. Diagnostic entry point for "is Ciel working?" questions.
 ---
 
 # /ciel-status — Ciel Environment Health Check
 
-*Displays the current Ciel environment status: version, skills, hooks, and config.*
+Displays the current Ciel environment status: version, platform, hooks, skills, agents, and config health.
 
 Usage: `/ciel-status [--check]`
 
-- `--check` — run diagnostics (verify hooks fire, skills load, config is valid)
+- No flag — summary view
+- `--check` — run full diagnostics (verify hooks fire, skills load, config valid)
 
-## Output
+## Summary output
 
 ```
 ## CIEL STATUS
 
-Version: v6.11.3
+Version: v4.0.1
 Platform: Claude Code
-Config: .claude/settings.json — OK (4 hooks registered)
-Skills directory: skills/ — 43 skills loaded
-Commands: 7 commands available
-Last session: 2026-05-06T11:20:00Z — Skills library reorg
+Config: .claude/settings.json — OK
+Hooks: 12 registered
+Skills: 48 domain skills in .claude/skills/
+Agents: 4 sub-agents (researcher, explorer, critic, improver)
+Commands: 7 available
+Memory: .ciel/memory/ — N episodes
 ```
 
 ## Diagnostics (--check)
 
-- [ ] CLAUDE.md readable and includes Ciel pipeline
-- [ ] .claude/settings.json valid JSON, hooks registered
-- [ ] .ciel/map.json parseable and up-to-date
-- [ ] .ciel/memory.json parseable
-- [ ] Shell hooks executable (check-test-first, block-destructive, track-file, meta-critiquer)
-- [ ] Skills directory non-empty and accessible
-- [ ] Agent definitions present (.claude/agents/ or .opencode/agents/)
+- CLAUDE.md readable and includes Ciel pipeline
+- .claude/settings.json valid JSON, all hooks registered
+- .ciel/map.json parseable
+- .ciel/memory/index.json present
+- Shell hooks executable and firing
+- Skills directory non-empty
+- Agent definitions present (4 files)
 
-## When triggered
+## When to use
 
-- User asks "is Ciel working?" or "check Ciel health"
-- After ciel-init to verify installation
+- After `/ciel-init` to verify installation
+- When "is Ciel working?" is asked
 - Debugging hook failures or missing depth classification

package/assets/commands/ciel-update.md

@@ -1,62 +1,43 @@
 ---
-description: Check GitHub for newer Ciel release and re-install. Runs `scripts/install.sh --check-update` then `--update`.
+description: Check GitHub for newer Ciel release and re-install. Preserves project config — ciel-overlay.md, .ciel/, settings.json.
 ---
 
 # /ciel-update — Update Ciel to the latest version
 
 Checks GitHub for a newer release and re-installs if available.
 
-## Steps
-
-1. **Check version**: `bash scripts/install.sh --check-update`
-   - Fetches `VERSION` from GitHub, compares with local
-   - Prints "up to date" or "update available"
-
-2. **Apply update**: `bash scripts/install.sh --update -y`
-   - Re-installs all Ciel files (plugins, agents, commands, hooks)
-   - Preserves: `ciel-overlay.md`, `.ciel/`, existing configs
-   - Non-destructive merge on `opencode.json`
+Usage: `/ciel-update [--check]`
 
-3. **npm update**: `npm update -g @neikyun/ciel`
-   - Updates the Ciel CLI tool from npm
-   - Skip if npm is not available or the package isn't installed globally
+- No flag — full update (check + apply)
+- `--check` — only check remote version, report, don't install
 
-## Flags
-
-| Flag | Purpose |
-|------|---------|
-| `--check-update` | Check remote version, don't install |
-| `--update` / `-u` | Force reinstall all files |
-| `-y` | Skip confirmation (non-interactive) |
-| `-q` | Quiet mode (summary only) |
-
-## One-liner
+## Steps
 
-```bash
-bash <(curl -fsSL https://raw.githubusercontent.com/KaosKyun/Ciel/main/scripts/install.sh) --check-update
-bash <(curl -fsSL https://raw.githubusercontent.com/KaosKyun/Ciel/main/scripts/install.sh) --update -y
-```
+1. **Check version**: fetch `VERSION` from GitHub, compare with `.ciel/version` or `VERSION`
+2. **Apply update**: re-install all Ciel files (hooks, agents, commands, skills, plugin)
+3. **Verify**: confirm hooks executable, agents present, config valid
 
 ## What's preserved
 
 - `ciel-overlay.md` — project-specific rules
-- `.ciel/map.json`, `.ciel/memory.json`, `.ciel/parking.md`
-- `opencode.json` — existing config merged non-destructively
-- `.claude/settings.json` — hook paths preserved
+- `.ciel/` — state directory (map.json, memory/, parking.md)
+- `.claude/settings.json` — merged non-destructively
+- `.opencode/opencode.json` — merged non-destructively
 
 ## What's replaced
 
-- `.opencode/plugins/ciel.ts` — fresh plugin
-- `.opencode/agents/ciel-*.md` — agent definitions
-- `.opencode/commands/ciel-*.md` — command files
-- `.claude/agents/ciel-*.md` — Claude Code agents
 - `.claude/hooks/*.sh` — shell hooks
-- `CLAUDE.md` — root instruction
+- `.claude/agents/ciel-*.md` — agent definitions
+- `.claude/commands/ciel-*.md` — command files
+- `.claude/skills/` — domain skills
+- `.opencode/plugins/ciel.ts` — plugin
+- `.opencode/agents/ciel-*.md` — OpenCode agents
+- `.opencode/commands/ciel*.md` — OpenCode commands
 
 ## Troubleshooting
 
 | Symptom | Fix |
 |---------|-----|
-| `Could not fetch remote version` | Check internet or proxy: `https_proxy=... bash install.sh --check-update` |
-| Plugin not loaded after update | Restart OpenCode (plugin loaded at session start) |
-| `jq not found` warning | Install jq for automatic opencode.json patching |
+| Could not fetch remote version | Check internet or proxy: `https_proxy=...` |
+| Plugin not loaded after update | Restart editor (plugin loaded at session start) |
+| Hook permissions after update | `chmod +x .claude/hooks/*.sh` |