shotgun: Instructions file for Claude Code

CLAUDE.md

shotgun CLAUDE.md is an instructions file for Claude Code from shotgun-sh/shotgun. It costs 3,724 tokens per session, scanned A, original, MIT.

Repository instructions for Shotgun, including how to run evaluations and add test cases that judge an AI agent's behavior. It explains when to use fixed checks and when to use a language model as the judge.

In plain words
What is it for?
Use it when running evaluations or adding cases that check responses, tool calls, delegated work, or other agent behavior.
Why use it?
It helps contributors write evaluations that distinguish correct behavior from plausible but incorrect behavior.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is shotgun-sh/shotgun's own configuration. It tells Claude Code how to work on shotgun 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 shotgun configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shotgun-sh/shotgun. 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/shotgun-sh/shotgun/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shotgun-sh/shotgun

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 shotgun CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shotgun-sh/shotgun/claude-md.svg)](https://agentmods.dev/instructions/shotgun-sh/shotgun/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shotgun-sh/shotgun/claude-md"><img src="https://agentmods.dev/badge/instructions/shotgun-sh/shotgun/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,724 This file is loaded in full into every session.
When invoked 3,724 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 $0.03724 $0.03724
Opus 5 $0.01862 $0.01862
Sonnet 5 $0.00745 $0.00745
Haiku 4.5 $0.00372 $0.00372

Measured 8d ago against content hash 65e7d891b1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shotgun 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 8d 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 · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions for Shotgun

Evals

To understand how to run the evals read evals/README.md

Writing Eval Test Cases

When adding new eval test cases with judge rubrics:

  1. Default to LLM as a judge - Unless the behavior being tested is purely deterministic (e.g., specific tool was called, specific field was populated), use the expected_response field to provide a rubric for the LLM judge to evaluate against.

  2. Write rubrics that describe correct vs incorrect behavior - The expected_response field should explain:

    • What the correct behavior looks like
    • What incorrect behaviors to watch for
    • Why the distinction matters
  3. Example rubric format:

    expected_response="""The Router should immediately use file_requests to load the PDF file.
    Correct behavior: Set file_requests with the PDF path, provide a brief acknowledgment.
    Incorrect behavior: Asking clarifying questions, claiming inability to access files, or delegating to another agent."""
    
  4. Use deterministic evaluators for structural checks - Things like disallowed_tools, disallowed_delegations, and response_not_contains are better as deterministic checks since they have clear pass/fail criteria.

Architecture Documentation

For detailed architecture documentation, see:

Commit Message Convention

This project enforces Conventional Commits specification. All commit messages MUST follow this format:

<type>[optional scope]: <description>

[optional body]

[optional footer(s)]

Required Commit Types

IMPORTANT: These types must stay in sync between cz_conventional_commits (pyproject.toml) and GitHub Actions (pr.yml).

Use these types for your commit messages:

  • feat: A new feature
  • fix: A bug fix
  • docs: Documentation only changes
  • style: Changes that don't affect code meaning (formatting, missing semicolons, etc.)
  • refactor: Code change that neither fixes a bug nor adds a feature
  • perf: Performance improvements
  • test: Adding missing tests or correcting existing tests
  • build: Changes that affect the build system or external dependencies
  • ci: Changes to CI configuration files and scripts
  • chore: Other changes that don't modify src or test files
  • revert: Reverts a previous commit

Read the full file on GitHub · 422 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. 8d ago First seen · 422 lines · 3,724 tokens per session scan A 65e7d891b1be

Subscribe to this mod's changes

shotgun CLAUDE.md is an instructions file published in the GitHub repository shotgun-sh/shotgun (682 stars, last pushed 3mo ago), licensed MIT. It adds 3,724 tokens to every session, about $0.0186 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens