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/samsantosb/ship-it/agents-mdgit clone --depth 1 https://github.com/samsantosb/ship-itWrote 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/samsantosb/ship-it/agents-md)<a href="https://agentmods.dev/instructions/samsantosb/ship-it/agents-md"><img src="https://agentmods.dev/badge/instructions/samsantosb/ship-it/agents-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 | $0.00973 | $0.00973 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
ship-it AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — running this pipeline on any agent
This pipeline is harness-agnostic by design: the skills are plain-markdown playbooks, the contracts are plain files, and the tools are git, gh/glab and file edits. Any capable coding agent — Kiro, opencode, OpenAI Codex, Gemini CLI, Cursor, Zed, aider, Claude Code, an OSS model on any harness — can run it by following this page. (The .claude-plugin/ manifests exist only for harnesses with native plugin support; nothing else depends on them.)
How to run a skill without a skill system
- Open
skills/<name>/SKILL.mdand follow it top to bottom as your instructions for the task. The user's argument (a card path, a PR number, an idea) is the skill's input. Ignore the YAML frontmatter — it is skill-system metadata for harnesses with native skill support (disable-model-invocationincluded). - Resolve
${CLAUDE_PLUGIN_ROOT}to this repository's root:${CLAUDE_PLUGIN_ROOT}/shared/guardrails.mdmeansshared/guardrails.mdhere. "Load before acting" means read those files before doing anything else. - When a skill hands off to another (
/watch-pr <PR>,/create-tasks <doc>), open that skill'sSKILL.mdand continue with the given argument.
Tool equivalences
The playbooks name a few tools by their Claude Code names (the reference harness for tool naming); substitute your harness's equivalent:
| In the playbooks | Use instead |
|---|---|
AskUserQuestion (batched, up to 4 questions, options with "(Recommended)") |
Ask in chat: numbered options, recommended option first, one message for the whole batch |
Grep / Glob / Read / Write tools |
Your search/read/write equivalents (rg, your editor tooling) |
| Skill chaining / slash commands | Open the referenced SKILL.md and keep going |
| Session scratchpad (watch-pr state file) | Any writable temp directory outside the target repo |
Resume commands in notifications (/do-task tasks/TASK-007.md) |
Write the invocation your harness understands — the human must be able to paste it |
| "User memory" (resolution step 3; personal facts like a Slack handle) | Your harness's memory store if it has one; otherwise skip that step and ask — personal facts never go into the repo either way |
MCP/connector registration (claude mcp add …, Connectors menu) |
Your harness's own MCP/connector mechanism; no MCP support → prefer the CLI paths (gh, glab) and local Markdown mode |
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.
- 5d ago First seen · 42 lines · 973 tokens per session scan A 97fb8ab0cfac
ship-it AGENTS.md is an instructions file published in the GitHub repository samsantosb/ship-it (23 stars, last pushed 1mo ago), licensed MIT. It adds 973 tokens to every session, about $0.0049 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.