Borrowing it
Nothing to install: this file belongs to dachhack/stathead. 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/dachhack/stathead/claude/nfl-fantasy-workbench-6D1yd/CLAUDE.mdgit clone --depth 1 https://github.com/dachhack/statheadWrote 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/dachhack/stathead/claude-md)<a href="https://agentmods.dev/instructions/dachhack/stathead/claude-md"><img src="https://agentmods.dev/badge/instructions/dachhack/stathead/claude-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/dachhack/stathead/claude-md"><img src="https://agentmods.dev/badge/instructions/dachhack/stathead/claude-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 | $0.00314 | $0.00314 |
| Opus 5.5 | $0.00126 | $0.00126 |
| Sonnet 5.5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
stathead CLAUDE.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 4d 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.
What it actually says
StatHead
Rule: third-party data is an input, never an output
Third-party rankings, values and projections (KTC, FantasyCalc, FantasyPros,
FFC, Sleeper, ESPN, PFF, Tankathon and the like) may feed StatHead's own
numbers, but must never be shown raw: not in the site, not in MCP tool output,
not in exports. Show StatHead blends, StatHead model outputs, or ranks computed
on StatHead values. Blends need at least two sources, and values fitted to a
market's scale must use a smooth curve, not the market's own numbers. See
docs/third-party-data-policy.md for what counts and where the helpers live.
One exception, by owner decision: the token-gated partner feed in
workers/stathead-sports may serve a single-market ADP to Drip; it is never
linked from the site, the MCP server or the Python package. A second, by
owner decision 2026-11-01: the site's Research > Sleeper Picks page shows the
Sleeper Picks lines StatHead leaned on, never Sleeper's payouts or pick
shares (scripts/build-pick-board.py allowlists the fields).
Notes
- The MCP server's source of truth is
mcp/dist/server.mjs(edited directly;npm run build:mcponly syntax-checks it). BumpSERVER_VERSIONthere andmcp/package.jsontogether.
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.
- 4d ago Changed · +3 lines · +57 tokens per session 6867e05611d8
- 1mo ago Changed · +3 lines · +50 tokens per session 5be6f751861e
- 1mo ago First seen · 18 lines · 207 tokens per session scan A ed8cd84fda72
stathead CLAUDE.md is an instructions file published in the GitHub repository dachhack/stathead (3 stars, last pushed yesterday), licensed MIT. It adds 314 tokens to every session, about $0.0013 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 2026-10-01.
stathead CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stathead CLAUDE.mddachhack/stathead | Instructions file | 3 | yesterday | MIT | A | 314 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |