biff CLAUDE.md

biff CLAUDE.md is an instructions file for Claude Code from punt-labs/biff. It costs 7,428 tokens per session, scanned A, original, MIT.

A set of coding rules for the biff project, covering code quality, testing, and how the repository is shared. It also explains why Git submodules are not used there.

In plain words
What is it for?
Writing, reviewing, and testing biff code; fixing problems found during work; and avoiding repository changes that could break installation.
Why use it?
It gives the coding agent consistent project standards and prevents avoidable problems, including installations that fail for users without GitHub SSH keys.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for biff CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/punt-labs/biff/claude-md.svg)](https://agentmods.dev/instructions/punt-labs/biff/claude-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 7,428 This file is loaded in full into every session.
When invoked 7,428 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07428 $0.07428
Opus 5 $0.03714 $0.03714
Sonnet 5 $0.01486 $0.01486
Haiku 4.5 $0.00743 $0.00743

Measured 5d ago against content hash 1079d8a6c35c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 5d 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.

CLAUDE.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 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.

Read the full file on GitHub · 461 lines

Changes

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.

  1. 5d ago First seen · 461 lines · 7,428 tokens per session scan A 1079d8a6c35c

Subscribe to this mod's changes

biff CLAUDE.md is an instructions file published in the GitHub repository punt-labs/biff (2 stars, last pushed 2d ago), licensed MIT. It adds 7,428 tokens to every session, about $0.0371 per session on Opus 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.