Borrowing it
Nothing to install: this file belongs to punt-labs/biff. 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/punt-labs/biff/main/CLAUDE.mdgit clone --depth 1 https://github.com/punt-labs/biffWrote 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/punt-labs/biff/claude-md)<a href="https://agentmods.dev/instructions/punt-labs/biff/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/biff/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/punt-labs/biff/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/biff/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 | $0.07379 | $0.07379 |
| Opus 5.5 | $0.02952 | $0.02952 |
| Sonnet 5.5 | $0.01476 | $0.01476 |
| Haiku 4.5 | $0.00738 | $0.00738 |
Grade A, and why
biff 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 3d 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How I Write Code
I am a principal engineer. Every change I make leaves the codebase in a better state than I found it. I do not excuse new problems by pointing at existing ones. I do not defer quality to a future ticket. I do not create tech debt.
No "Pre-existing" Excuse
There is no such thing as a "pre-existing" issue. If you see a problem — in code you wrote, code a reviewer flagged, or code you happen to be reading — you fix it. Do not classify issues as "pre-existing" to justify ignoring them. Do not suggest that something is "outside the scope of this change." If it is broken and you can see it, it is your problem now.
No Git Submodules
This repo is cloned onto every user's machine. claude plugin install biff@punt-labs clones it, and it clones with submodules. Everything tracked here ships to every consumer.
So the org-wide rule "every project adds punt-labs/team as a submodule at .punt-labs/ethos/" does not apply to biff. It was added, and it broke keyless installs: .gitmodules used the SSH URL [email protected]:punt-labs/team.git, so any user without a GitHub SSH key hit
fatal: clone of '[email protected]:punt-labs/team.git' into submodule path ... failed
Failed to clone '.punt-labs/ethos' a second time, aborting
punt-labs/team being public does not help — SSH auth fails before repo visibility is consulted. An HTTPS URL would fix the auth failure but still push 1.1 MB of internal identity data onto every user's disk. Do not re-add it.
What remains under .punt-labs/ is ordinary tracked content, not a submodule, and it is deliberately two files:
| File | Why it stays |
|---|---|
.punt-labs/ethos.yaml |
Names this repo's agent (claude). Located by _find_ethos_config(), then parsed by _read_agent_handle() for the agent field. |
.punt-labs/ethos/identities/claude.yaml |
The only file biff's runtime consumes from the org registry — see below. |
claude.yaml is not an arbitrary subset. resolve_agent_identity_from_disk() (DES-040) reads it to give an agent session agent-first identity, and _known_agent_github_logins() (DES-053) scans that directory for every kind: agent identity's github login so a leaked bot PAT can be rejected. claude.yaml is the only agent identity in the entire org registry carrying a github field, so it alone carries that security property. The global ~/.punt-labs/ethos/ cannot substitute — it holds the human identity, not claude.
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.
- 3d ago Changed · +1 lines · +14 tokens per session 06cb70be63b7
- 11d ago Changed · -11 lines · -63 tokens per session 8bafff318127
- 2mo ago First seen · 461 lines · 7,428 tokens per session scan A 1079d8a6c35c
biff CLAUDE.md is an instructions file published in the GitHub repository punt-labs/biff (2 stars, last pushed today), licensed MIT. It adds 7,379 tokens to every session, about $0.0295 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.
biff CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| biff CLAUDE.mdpunt-labs/biff | Instructions file | 2 | today | MIT | A | 7,379 | 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 |