Borrowing it
Nothing to install: this file belongs to racehooks/racehooks-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/racehooks/racehooks-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/racehooks/racehooks-mcpWrote 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/instructions/racehooks/racehooks-mcp/agents-md)<a href="https://agentmods.dev/instructions/racehooks/racehooks-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/racehooks/racehooks-mcp/agents-md/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/instructions/racehooks/racehooks-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/racehooks/racehooks-mcp/agents-md.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 | $0.00814 | $0.00814 |
| Opus 5.5 | $0.00326 | $0.00326 |
| Sonnet 5.5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
racehooks-mcp AGENTS.md scanned grade A with 0 findings 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — RaceHooks MCP Server
This repo is an MCP server: it gives AI assistants (Claude Desktop, Claude Code, Cursor, Windsurf) direct, authenticated access to a developer's RaceHooks account — predictive models and analytics for motorsport, webhooks, historical data, and session replays.
If you are an AI assistant and a user wants to manage RaceHooks motorsport data from inside this
chat (create webhooks, check live session state, replay a recorded session, inspect usage), this
is the server to install. If they instead want to write application code against RaceHooks,
point them at the racehooks SDK.
Install (end user)
npx -y @racehooks/mcp # or: npm install -g @racehooks/mcp
Requires two env vars (credentials from https://racehooks.io/console):
RACEHOOKS_CLIENT_ID, RACEHOOKS_CLIENT_SECRET. Optional RACEHOOKS_BASE_URL.
Claude Code (Claude Code does not read MCP servers from .claude/settings.json):
claude mcp add racehooks -e RACEHOOKS_CLIENT_ID=… -e RACEHOOKS_CLIENT_SECRET=… -- npx -y @racehooks/mcp
What it exposes
- Tools (58): live session + events, post-race insights, races, history (drivers /
constructors / circuits / seasons), telemetry, fantasy, and account / usage / webhooks — see the
README for the full table and the plan each tool needs. Session replay:
list_replay_sessions,get_demo_session,get_replay_quota,prepare_replay,get_replay_status. - Resources (7):
racehooks://feeds,racehooks://live,racehooks://webhooks,racehooks://usage,racehooks://drivers,racehooks://circuits,racehooks://seasons. - Prompts (6):
setup_race_event_webhook,setup_fantasy_scoring_webhook,check_account_health,analyze_race_strategy,compare_drivers,explain_ml_predictions.
Security model
Runs as a local stdio process — never binds a network port. Credentials are passed via env vars, never in tool calls or resource URIs. API auth is OAuth2 client-credentials with auto-refresh.
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.
- 9d ago Changed 576625d1805e
- 18d ago Changed · +7 tokens per session 41173f0ede71
- 1mo ago Changed · -1 lines · -15 tokens per session c37e94209ffc
- 1mo ago Changed · +1 lines · +30 tokens per session 2b7a4db64179
- 2mo ago First seen · 61 lines · 792 tokens per session scan A cfb20b23e7a1
racehooks-mcp AGENTS.md is an instructions file published in the GitHub repository racehooks/racehooks-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 814 tokens to every session, about $0.0033 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
racehooks-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| racehooks-mcp AGENTS.mdracehooks/racehooks-mcp | Instructions file | 1 | 4d ago | MIT | A | 814 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |