Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/brain-bootstrap/claude-code-brain-bootstrap/mcp)<a href="https://agentmods.dev/commands/brain-bootstrap/claude-code-brain-bootstrap/mcp"><img src="https://agentmods.dev/badge/commands/brain-bootstrap/claude-code-brain-bootstrap/mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/brain-bootstrap/claude-code-brain-bootstrap/mcp"><img src="https://agentmods.dev/badge/commands/brain-bootstrap/claude-code-brain-bootstrap/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00919 |
| Opus 5.5 | $0.00007 | $0.00368 |
| Sonnet 5.5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade B, and why
mcp scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- **NEVER** hardcode API keys in `.mcp.json` — use env var placeholders like `"YOUR_API_KEY_HERE"` How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Model Context Protocol (MCP) servers for this project: $ARGUMENTS
ultrathink — use extended reasoning for MCP server selection and configuration.
MCP Tool Invocation Format
Once servers are configured in .mcp.json, invoke their tools using:
mcp__SERVER_KEY__TOOL_FUNCTION_NAME
Where SERVER_KEY is the key in .mcp.json under mcpServers.
Instructions
If $ARGUMENTS contains list or is empty:
- Read
.mcp.jsonto show currently configured servers - Show the invocation format for each tool
- Suggest additional servers based on the tech stack in
claude/architecture.md
If $ARGUMENTS contains add <server-name>:
- Check if the server name exists in the Smithery Registry:
https://registry.smithery.ai/servers/<name> - Add the server configuration to
.mcp.jsonundermcpServers - Update
.claude/settings.jsonto includeallowedToolspermissions for the new server - Update
CLAUDE.md— add a note to the Plugin Ecosystem or Critical Patterns section
If $ARGUMENTS contains status:
- Read
.mcp.json— list all configured servers with their connection type - Check which tools each server provides
- Verify
allowedToolsin.claude/settings.jsonis in sync with.mcp.json
If $ARGUMENTS contains format or invocations:
Show all available MCP tool invocations from the current .mcp.json:
mcp__SERVER_KEY__TOOL_NAME
Common MCP Servers by Project Type
Web / Frontend projects
github—mcp__github__create_pull_request,mcp__github__list_commitsweb-search—mcp__web-search__search(documentation lookup)filesystem—mcp__filesystem__read_file,mcp__filesystem__write_file
Backend / API projects
postgres—mcp__postgres__query(read-only DB access)github— PR management, issue trackingweb-search— API documentation, best practices
Data Science / ML projects
filesystem— data file accessweb-search— research papers, library docsdocuments— reading large datasets or PDFs
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 108 lines · 18 tokens per session scan B 2603bf5ac257
mcp is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 919 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
restart
Restart the Claude Mnemonic worker process.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.