prfaq CLAUDE.md

prfaq CLAUDE.md is an instructions file for Claude Code from punt-labs/prfaq. It costs 5,380 tokens per session, scanned A, original, MIT.

A repository guide for how an engineering team expects code changes to be made and reviewed. It includes a required workflow, quality standards, and checks for templates and agent-skill prompts.

In plain words
What is it for?
Use it when changing code in the prfaq repository, especially its LaTeX templates, workflow files, or skill instructions.
Why use it?
It gives the coding agent a fixed process to follow and requires visible problems to be addressed instead of dismissed as old issues. This reduces skipped reviews, broken templates, and untested prompt changes.

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 prfaq CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/punt-labs/prfaq/claude-md.svg)](https://agentmods.dev/instructions/punt-labs/prfaq/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/punt-labs/prfaq/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/prfaq/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,380 This file is loaded in full into every session.
When invoked 5,380 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 $0.05380 $0.05380
Opus 5 $0.02690 $0.02690
Sonnet 5 $0.01076 $0.01076
Haiku 4.5 $0.00538 $0.00538

Measured today against content hash 394e08b050d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prfaq 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 today.

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 · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 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.

Mandatory Reading

@docs/WORKFLOW.md

WORKFLOW.md is the three-loop development process (backlog → PR → delegation) that governs every change to this repo, no matter how small it looks. Read it before writing or editing anything — it is the enforcement mechanism for the branch/bead/review discipline described below.

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.

Standards

  • Templates compile. Every change to .tex files must produce a valid PDF via pdflatex. Broken templates are broken features.
  • Skill prompts are tested. After modifying SKILL.md or reference guides, run /prfaq to verify the skill produces correct output.
  • Reference guides are self-contained. Each guide in plugin/skills/prfaq/references/ stands alone — no forward references to guides that don't exist yet.
  • Duplication is a design failure. The template defines environments once. The dogfood prfaq.tex should match the template's environment definitions.
  • Version numbers are synchronized. plugin.json, install.sh, and README.md must agree on the version.
  • Backwards compatibility shims do not exist. When code changes, callers change. No dead re-exports, no # removed tombstones.

Development Workflow

Branch Discipline

Nothing lands on main except through a merged PR — no exceptions, no bypass-rights shortcuts. Every change, including a one-line typo fix, goes through a branch. What varies by size is only the branch's name and lifetime, never whether it exists:

Read the full file on GitHub · 380 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. today Changed · +5 lines · +63 tokens per session 394e08b050d6
  2. 6d ago First seen · 375 lines · 5,317 tokens per session scan A 914f7f5b5426

Subscribe to this mod's changes

prfaq CLAUDE.md is an instructions file published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 4d ago), licensed MIT. It adds 5,380 tokens to every session, about $0.0269 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 2026-08-30.