Name: cerebro-setup
Author: yelaco

Prompt file imported from yelaco/claude-xmen (.claude/commands/cerebro-setup.md). Copyright stays with the author.

Cerebro Setup — Initialize and Verify Installation

Run after cloning the template or any time the installation feels misconfigured. Wires CLAUDE.md correctly and checks whether the upstream template has a newer release.

Instructions for Cerebro

This is a Cerebro-led single-flow operation. Do NOT create an agent team. Do NOT touch .cerebro/.pending-todos or .cerebro/pending-todos/. Do NOT spawn Wolverine or Storm. Handle everything directly, like /cerebro-doctor.

Upstream remote: https://github.com/yelaco/claude-xmen.git

1. Wire and Check Installation

Run the setup status helper. It prepends the Cerebro identity import to CLAUDE.md if missing, verifies .cerebro/cerebro-identity.md, reads .cerebro/upgrade-state.json when present, and checks the latest upstream tag.

test -f .cerebro/scripts/setup-status.py
python3 .cerebro/scripts/setup-status.py --upstream https://github.com/yelaco/claude-xmen.git

If upstream is unreachable, the helper skips version comparison and reports latest upstream - unreachable.

2. Semble Integration (Optional)

Ask the user whether they want to enable semble for semantic code search:

Semble is an optional MCP integration that gives Nightcrawler natural-language code search — ~98% fewer tokens than grep+read, fully on CPU, no API key.

Enable semble? (yes / no)

If yes:

Check whether it is already registered:

claude mcp list 2>/dev/null | grep -i semble && echo "already registered" || echo "not registered"

If already registered, skip to step 3.

Detect the available installer and register the MCP server:
```
which uv 2>/dev/null && echo "uv" || (which pip3 2>/dev/null || which pip 2>/dev/null) && echo "pip" || echo "none"
```
- uv found:
```
claude mcp add semble -s user -- uvx --from "semble[mcp]" --with model2vec semble
```
- pip found (no uv): Install semble first, then register with the bare command:
```
pip install "semble[mcp]"
claude mcp add semble -s user -- semble
```
  Report:
  
  Installed semble via pip. If semble is not on $PATH after install, you may need to restart your shell or add your pip bin directory to $PATH.
- Neither found: Warn the user and skip:
  Neither uv nor pip was found. Install one of them and re-run /cerebro-setup to enable semble:
  - uv (recommended): curl -LsSf https://astral.sh/uv/install.sh | sh
  - pip: ships with Python — install Python from https://python.org
  Set semble status to SKIPPED (no installer) in the summary and do not create the integration file.
Create .cerebro/integrations/semble.md only if it does not already exist. If the file is already present, skip this step — do not overwrite it. If it is absent, write it with this exact content (copy from .cerebro/integrations/semble.md in the upstream template if present, otherwise write verbatim):

# Semble — Semantic Code Search

Semble is installed as an MCP server. The following teammates should prefer it over grep for natural-language and conceptual queries: **Nightcrawler**, **Wolverine**, and **Forge**.

## MCP Tools

- `mcp__semble__search(query, repo)` — natural-language or identifier search; `repo` is a local path or git URL; defaults to the current working directory.
- `mcp__semble__find_related(file_path, line, repo)` — find chunks semantically similar to the code at a given file location.

## When to Use Semble

- Conceptual / natural-language queries → `mcp__semble__search`
- "Find code similar to X" → `mcp__semble__find_related`
- Exhaustive exact-string or regex matching → use `grep` (semble is not a text matcher)

## Per-Teammate Guidance

**Nightcrawler** — primary user. Prefer semble for all conceptual queries; fall back to grep only for exact-string or regex matching.

**Wolverine** — use `mcp__semble__search` before implementing to find existing patterns, conventions, and similar code to avoid duplication. Use `mcp__semble__find_related` to discover all call sites when changing an interface.

**Forge** — use `mcp__semble__search` to locate architectural examples and assess how widely a pattern is used before recommending changes. Use `mcp__semble__find_related` to find the blast radius of a design decision.

## Indexing for Repeated Searches

Index once for faster repeated queries:
```bash
semble index . -o .cerebro/semble-index
```
Pass `--index .cerebro/semble-index` to searches. Reindex if the codebase changes significantly.

Report:

Semble MCP registered and integration file written to .cerebro/integrations/semble.md. Nightcrawler will use it on the next team dispatch.

If no: skip silently.

3. Summary

Print a brief setup report:

CLAUDE.md import     — PRESENT | FIXED
cerebro-identity.md  — PRESENT | MISSING
installed version    — <ref> | unknown
latest upstream      — <ref> | unreachable
upgrade needed       — YES | NO | UNKNOWN
semble integration   — ENABLED | SKIPPED | SKIPPED (no installer)

Install cerebro-setup and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# Cerebro Setup — Initialize and Verify Installation Run after cloning the template or any time the installation feels misconfigured. Wires `CLAUDE.md` correctly and checks whether the upstream template has a newer release. ## Instructions for Cerebro This is a **Cerebro-led single-flow operation**. Do NOT create an agent team. Do NOT touch `.cerebro/.pending-todos` or `.cerebro/pending-todos/`. Do NOT spawn Wolverine or Storm. Handle everything directly, like `/cerebro-doctor`. Upstream remote: `https://github.com/yelaco/claude-xmen.git` --- ### 1. Wire and Check Installation Run the setup status helper. It prepends the Cerebro identity import to `CLAUDE.md` if missing, verifies `.cerebro/cerebro-identity.md`, reads `.cerebro/upgrade-state.json` when present, and checks the latest upstream tag. ```bash test -f .cerebro/scripts/setup-status.py python3 .cerebro/scripts/setup-status.py --upstream https://github.com/yelaco/claude-xmen.git ``` If upstream is unreachable, the helper skips version comparison and reports `latest upstream - unreachable`. --- ### 2. Semble Integration (Optional) Ask the user whether they want to enable semble for semantic code search: > **Semble** is an optional MCP integration that gives Nightcrawler natural-language code search — ~98% fewer tokens than grep+read, fully on CPU, no API key. > > Enable semble? **(yes / no)** **If yes:** 1. Check whether it is already registered: ```bash claude mcp list 2>/dev/null | grep -i semble && echo "already registered" || echo "not registered" ``` If already registered, skip to step 3. 2. Detect the available installer and register the MCP server: ```bash which uv 2>/dev/null && echo "uv" || (which pip3 2>/dev/null || which pip 2>/dev/null) && echo "pip" || echo "none" ``` - **`uv` found:** ```bash claude mcp add semble -s user -- uvx --from "semble[mcp]" --with model2vec semble ``` - **`pip` found (no `uv`):** Install semble first, then register with the bare command: ```bash pip install "semble[mcp]" claude mcp add semble -s user -- semble ``` Report: > Installed semble via pip. If `semble` is not on `$PATH` after install, you may need to restart your shell or add your pip bin directory to `$PATH`. - **Neither found:** Warn the user and skip: > Neither `uv` nor `pip` was found. Install one of them and re-run `/cerebro-setup` to enable semble: > - **uv (recommended):** `curl -LsSf https://astral.sh/uv/install.sh | sh` > - **pip:** ships with Python — install Python from https://python.org Set semble status to `SKIPPED (no installer)` in the summary and do not create the integration file. 3. Create `.cerebro/integrations/semble.md` **only if it does not already exist**. If the file is already present, skip this step — do not overwrite it. If it is absent, write it with this exact content (copy from `.cerebro/integrations/semble.md` in the upstream template if present, otherwise write verbatim): ```markdown # Semble — Semantic Code Search Semble is installed as an MCP server. The following teammates should prefer it over grep for natural-language and conceptual queries: **Nightcrawler**, **Wolverine**, and **Forge**. ## MCP Tools - `mcp__semble__search(query, repo)` — natural-language or identifier search; `repo` is a local path or git URL; defaults to the current working directory. - `mcp__semble__find_related(file_path, line, repo)` — find chunks semantically similar to the code at a given file location. ## When to Use Semble - Conceptual / natural-language queries → `mcp__semble__search` - "Find code similar to X" → `mcp__semble__find_related` - Exhaustive exact-string or regex matching → use `grep` (semble is not a text matcher) ## Per-Teammate Guidance **Nightcrawler** — primary user. Prefer semble for all conceptual queries; fall back to grep only for exact-string or regex matching. **Wolverine** — use `mcp__semble__search` before implementing to find existing patterns, conventions, and similar code to avoid duplication. Use `mcp__semble__find_related` to discover all call sites when changing an interface. **Forge** — use `mcp__semble__search` to locate architectural examples and assess how widely a pattern is used before recommending changes. Use `mcp__semble__find_related` to find the blast radius of a design decision. ## Indexing for Repeated Searches Index once for faster repeated queries: ```bash semble index . -o .cerebro/semble-index ``` Pass `--index .cerebro/semble-index` to searches. Reindex if the codebase changes significantly. ``` 4. Report: > Semble MCP registered and integration file written to `.cerebro/integrations/semble.md`. Nightcrawler will use it on the next team dispatch. **If no:** skip silently. --- ### 3. Summary Print a brief setup report: ``` CLAUDE.md import — PRESENT | FIXED cerebro-identity.md — PRESENT | MISSING installed version — <ref> | unknown latest upstream — <ref> | unreachable upgrade needed — YES | NO | UNKNOWN semble integration — ENABLED | SKIPPED | SKIPPED (no installer) ```

{ "prompt": "# Cerebro Setup — Initialize and Verify Installation\n\nRun after cloning the template or any time the installation feels misconfigured. Wires `CLAUDE.md` correctly and checks whether the upstream template has a newer release.\n\n## Instructions for Cerebro\n\nThis is a **Cerebro-led single-flow operation**. Do NOT create an agent team. Do NOT touch `.cerebro/.pending-todos` or `.cerebro/pending-todos/`. Do NOT spawn Wolverine or Storm. Handle everything directly, like `/cerebro-doctor`.\n\nUpstream remote: `https://github.com/yelaco/claude-xmen.git`\n\n---\n\n### 1. Wire and Check Installation\n\nRun the setup status helper. It prepends the Cerebro identity import to `CLAUDE.md` if missing, verifies `.cerebro/cerebro-identity.md`, reads `.cerebro/upgrade-state.json` when present, and checks the latest upstream tag.\n\n```bash\ntest -f .cerebro/scripts/setup-status.py\npython3 .cerebro/scripts/setup-status.py --upstream https://github.com/yelaco/claude-xmen.git\n```\n\nIf upstream is unreachable, the helper skips version comparison and reports `latest upstream - unreachable`.\n\n---\n\n### 2. Semble Integration (Optional)\n\nAsk the user whether they want to enable semble for semantic code search:\n\n> **Semble** is an optional MCP integration that gives Nightcrawler natural-language code search — ~98% fewer tokens than grep+read, fully on CPU, no API key.\n>\n> Enable semble? **(yes / no)**\n\n**If yes:**\n\n1. Check whether it is already registered:\n ```bash\n claude mcp list 2>/dev/null | grep -i semble && echo \"already registered\" || echo \"not registered\"\n ```\n If already registered, skip to step 3.\n\n2. Detect the available installer and register the MCP server:\n ```bash\n which uv 2>/dev/null && echo \"uv\" || (which pip3 2>/dev/null || which pip 2>/dev/null) && echo \"pip\" || echo \"none\"\n ```\n - **`uv` found:**\n ```bash\n claude mcp add semble -s user -- uvx --from \"semble[mcp]\" --with model2vec semble\n ```\n - **`pip` found (no `uv`):** Install semble first, then register with the bare command:\n ```bash\n pip install \"semble[mcp]\"\n claude mcp add semble -s user -- semble\n ```\n Report:\n > Installed semble via pip. If `semble` is not on `$PATH` after install, you may need to restart your shell or add your pip bin directory to `$PATH`.\n - **Neither found:** Warn the user and skip:\n > Neither `uv` nor `pip` was found. Install one of them and re-run `/cerebro-setup` to enable semble:\n > - **uv (recommended):** `curl -LsSf https://astral.sh/uv/install.sh | sh`\n > - **pip:** ships with Python — install Python from https://python.org\n \n Set semble status to `SKIPPED (no installer)` in the summary and do not create the integration file.\n\n3. Create `.cerebro/integrations/semble.md` **only if it does not already exist**. If the file is already present, skip this step — do not overwrite it. If it is absent, write it with this exact content (copy from `.cerebro/integrations/semble.md` in the upstream template if present, otherwise write verbatim):\n\n```markdown\n# Semble — Semantic Code Search\n\nSemble is installed as an MCP server. The following teammates should prefer it over grep for natural-language and conceptual queries: **Nightcrawler**, **Wolverine**, and **Forge**.\n\n## MCP Tools\n\n- `mcp__semble__search(query, repo)` — natural-language or identifier search; `repo` is a local path or git URL; defaults to the current working directory.\n- `mcp__semble__find_related(file_path, line, repo)` — find chunks semantically similar to the code at a given file location.\n\n## When to Use Semble\n\n- Conceptual / natural-language queries → `mcp__semble__search`\n- \"Find code similar to X\" → `mcp__semble__find_related`\n- Exhaustive exact-string or regex matching → use `grep` (semble is not a text matcher)\n\n## Per-Teammate Guidance\n\n**Nightcrawler** — primary user. Prefer semble for all conceptual queries; fall back to grep only for exact-string or regex matching.\n\n**Wolverine** — use `mcp__semble__search` before implementing to find existing patterns, conventions, and similar code to avoid duplication. Use `mcp__semble__find_related` to discover all call sites when changing an interface.\n\n**Forge** — use `mcp__semble__search` to locate architectural examples and assess how widely a pattern is used before recommending changes. Use `mcp__semble__find_related` to find the blast radius of a design decision.\n\n## Indexing for Repeated Searches\n\nIndex once for faster repeated queries:\n```bash\nsemble index . -o .cerebro/semble-index\n```\nPass `--index .cerebro/semble-index` to searches. Reindex if the codebase changes significantly.\n```\n\n4. Report:\n > Semble MCP registered and integration file written to `.cerebro/integrations/semble.md`. Nightcrawler will use it on the next team dispatch.\n\n**If no:** skip silently.\n\n---\n\n### 3. Summary\n\nPrint a brief setup report:\n\n```\nCLAUDE.md import — PRESENT | FIXED\ncerebro-identity.md — PRESENT | MISSING\ninstalled version — <ref> | unknown\nlatest upstream — <ref> | unreachable\nupgrade needed — YES | NO | UNKNOWN\nsemble integration — ENABLED | SKIPPED | SKIPPED (no installer)\n```", "variables": [], "notes": "Run after cloning the template or any time the installation feels misconfigured. Wires `CLAUDE.md` correctly and checks whether the upstream template has a newer release.", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/yelaco/claude-xmen", "path": ".claude/commands/cerebro-setup.md", "ref": "33503ef7008cccc7ce98497b98d3c257c5df4b13", "url": "https://github.com/yelaco/claude-xmen/blob/33503ef7008cccc7ce98497b98d3c257c5df4b13/.claude/commands/cerebro-setup.md", "key": "yelaco/claude-xmen/.claude/commands/cerebro-setup.md" } } }

cerebro-setup

About

Cerebro Setup — Initialize and Verify Installation

Instructions for Cerebro

1. Wire and Check Installation

2. Semble Integration (Optional)

3. Summary

Install cerebro-setup and it becomes one more candidate the router can pick - when it fits.

Use it

Manifest

Reviews