Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/threemoonslab/agents-shipgate/claude-mdgit clone --depth 1 https://github.com/ThreeMoonsLab/agents-shipgateWrote 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/threemoonslab/agents-shipgate/claude-md)<a href="https://agentmods.dev/instructions/threemoonslab/agents-shipgate/claude-md"><img src="https://agentmods.dev/badge/instructions/threemoonslab/agents-shipgate/claude-md.svg" alt="Measured on agentmods" 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 | $0.00787 | $0.00787 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
agents-shipgate 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions
The full agent-facing instructions for this repo live in AGENTS.md. Everything there applies to Claude Code.
A few Claude-specific notes:
Running the CLI in this repository
Use ./shipgate <command> ... from the repository root — the repository launcher, and the canonical command here (python shipgate <command> ... on Windows, which does not read a shebang). It is the same CLI as agents-shipgate, but it runs this working tree's src/, picks a supported interpreter (the main checkout's virtualenv when you are in a git worktree), and needs no install and no PYTHONPATH. The recovery commands it prints name the launcher, so you can run them as printed.
A bare agents-shipgate may resolve to a different, older install on PATH, or fail with ModuleNotFoundError if the environment behind it is gone. Use it only to check what an installed build does. If a command behaves as though an edit never happened, run ./shipgate doctor --config shipgate.yaml --json and read the environment block — it names the interpreter, the imported package, the checkout, and any mismatches[].
Permissions
agents-shipgate scan,preflight,init,doctor,explain,list-checks,fixture,self-checkare read-only with respect to user code; safe to run without confirmation.agents-shipgate init --writewritesshipgate.yamlin the workspace. Confirm before running on an unfamiliar repo.agents-shipgate init --write --agent-instructions=...writes/updatesAGENTS.md,CLAUDE.md,.cursor/rules/agents-shipgate.mdc, and the PR template via managed-block markers. Idempotent; confirm before running on an unfamiliar repo.agents-shipgate baseline savewrites one JSON file under.agents-shipgate/. Safe to run; reversible.
Output handling
Prefer --json on every command and parse the result programmatically. Do not scrape stdout when a JSON form exists. The stable JSON shape is the contract.
For scan, parse agents-shipgate-reports/report.json directly — that's where the structured output lives. The stdout summary is for humans.
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.
- 6d ago First seen · 37 lines · 787 tokens per session scan A e8e5c0fe144d
agents-shipgate CLAUDE.md is an instructions file published in the GitHub repository ThreeMoonsLab/agents-shipgate (87 stars, last pushed yesterday), licensed Apache-2.0. It adds 787 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
run-gemini-cli GEMINI.md
Instructions for google-github-actions/run-gemini-cli, covering guidelines for developing this github action, core principles for this action and your role in development.
local-ci CLAUDE.md
Claude Code instructions for redwoodjs/local-ci, covering local ci — agent instructions, rules, ci and code.
local-ci AGENTS.md
AGENTS.md instructions for redwoodjs/local-ci, a project described as: Run GitHub Actions locally — pause on failure, retry in place, and keep caches on your machine.
ai-news-agent AGENTS.md
AGENTS.md instructions for nickzren/ai-news-agent, covering ai news agent, purpose, preferred agent flow, defaults and status artifacts.
pipelines CLAUDE.md
Claude Code instructions for rios0rios0/pipelines, covering claude.md, what this is, commands, architecture and 5-stage pipeline model.
github-agentic-workflows copilot-instructions.md
Instructions for zircote-plugins/github-agentic-workflows, covering copilot instructions — aw-author plugin, project identity, repository structure, branching strategy and daily pipeline (.github/workflows/daily-intelligence.md).