zapat: Instructions file for Claude Code

CLAUDE.md

zapat CLAUDE.md is an instructions file for Claude Code from zapat-ai/zapat. It costs 2,760 tokens per session, scanned A, original, MIT.

Repository instructions for Zapat, an automated development pipeline driven by Claude Code and GitHub labels. They explain setup, available labels, commands, and when work is researched, planned, implemented, tested, reviewed, or held.

In plain words
What is it for?
Use them when configuring Zapat, checking its health, or deciding which label should trigger work on an issue or pull request.
Why use it?
They make the pipeline’s label-based behaviour understandable and help agents follow the project’s operating rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is zapat-ai/zapat's own configuration. It tells Claude Code how to work on zapat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zapat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zapat-ai/zapat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zapat-ai/zapat/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zapat-ai/zapat

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 zapat CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zapat-ai/zapat/claude-md/github.svg)](https://agentmods.dev/instructions/zapat-ai/zapat/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zapat-ai/zapat/claude-md"><img src="https://agentmods.dev/badge/instructions/zapat-ai/zapat/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.

agentmods 80×15 button for zapat CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zapat-ai/zapat/claude-md"><img src="https://agentmods.dev/badge/instructions/zapat-ai/zapat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,760 This file is loaded in full into every session.
When invoked 2,760 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02760 $0.02760
Opus 5 $0.01380 $0.01380
Sonnet 5 $0.00552 $0.00552
Haiku 4.5 $0.00276 $0.00276

Measured 9d ago against content hash 2c5d772d47c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zapat 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 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.

CLAUDE.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zapat

Zapat is an autonomous dev pipeline framework powered by Claude Code. It triages GitHub issues, implements features, runs tests, reviews code, and auto-merges -- all triggered by a single label.

Getting Started

If .env does not exist, run /zapat (from the repo) or /zapat:setup (from the plugin) to configure Zapat for your project.

If already configured, run /pipeline-check or /zapat:pipeline-check to verify everything is healthy.

Quick Reference

Labels

Label Description
agent Let the pipeline handle this (works on issues and PRs)
agent-work Skip triage, implement immediately
agent-research Research and analyze, don't code
agent-write-tests Write tests for the specified code
agent-plan Proposed work, pending human approval (not auto-implemented)
agent-phase-2 Phase 2 work, awaiting Phase 1 completion
agent-phase-3 Phase 3 work, awaiting Phase 2 completion
hold Block auto-merge on this PR
human-only Pipeline should not touch this
agent-full-review Force full team review regardless of complexity
codex Process with OpenAI Codex
claude Process with Claude Code

Status labels are managed automatically by the pipeline:

Label Meaning
zapat-triaging Triage in progress
zapat-implementing Implementation in progress
zapat-review Code review pending
zapat-testing Tests running
zapat-researching Research in progress
zapat-rework Addressing review feedback
zapat-visual Visual verification in progress
zapat-ci-fix CI auto-fix in progress
needs-rebase Auto-rebase failed due to conflicts (manual resolution needed)

Classification labels (applied during triage):

Label Description
feature New feature
bug Bug fix
tech-debt Technical debt
security Security issue
research Research task

Read the full file on GitHub · 245 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. 9d ago First seen · 245 lines · 2,760 tokens per session scan A 2c5d772d47c2

Subscribe to this mod's changes

zapat CLAUDE.md is an instructions file published in the GitHub repository zapat-ai/zapat (11 stars, last pushed 6mo ago), licensed MIT. It adds 2,760 tokens to every session, about $0.0138 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens