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/fortrabbit/agent-skills/agents-mdgit clone --depth 1 https://github.com/fortrabbit/agent-skillsWrote 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/fortrabbit/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/fortrabbit/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/fortrabbit/agent-skills/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 | $0.00605 | $0.00605 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
agent-skills 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to OpenAI Codex when working on this repository.
Project overview
fortrabbit/agent-skills is a multi-platform AI skills package for managing PHP web applications hosted on fortrabbit. It ships instructional content consumed by Claude Code, OpenAI Codex, and GitHub Copilot — there is no build step, no compiled code, and no tests.
Architecture
The project provides the same operational guidance in platform-specific formats:
| File / Path | Platform |
|---|---|
skills/fortrabbit/SKILL.md |
Claude Code + OpenAI Codex (canonical source) |
skills/fortrabbit-api-access/SKILL.md |
Claude Code + OpenAI Codex — MCP OAuth install + Public API tokens |
AGENTS.md |
OpenAI Codex contributor context (this file) |
.github/instructions/fortrabbit.instructions.md |
GitHub Copilot |
skills/fortrabbit/SKILL.md is the canonical source. When updating operational guidance, propagate changes to .github/instructions/fortrabbit.instructions.md.
Skill reference files
skills/fortrabbit/references/ contains operation guides loaded contextually by SKILL.md:
setup.md— SSH key setup and connection troubleshootingdeploy.md— Git push and deploy hook workflowsssh-exec.md— Remote command syntax per frameworkdatabase.md— SSH tunnel setup and DB pull/push proceduressync-content.md— Per-framework rsync paths and examples
Key conventions
Config lookup chain (in order):
.fortrabbitfile (app-env-id,region) — committed, no secrets.env(FORTRABBIT_APP_ENV_ID,FORTRABBIT_REGION,FORTRABBIT_DEPLOY_HOOK_SECRET)- Prompt the user if neither exists
Project type detection (file/dependency signals):
artisanfile orlaravel/frameworkin composer.json → Laravelcraftcms/cmsin composer.json → Craft CMSstatamic/cms→ Statamicgetkirby/cms→ Kirbywp-config.php→ WordPress- Other
composer.json→ Generic PHP
SSH host pattern: [email protected]
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.
- 4d ago First seen · 58 lines · 605 tokens per session scan A 26953625e303
agent-skills AGENTS.md is an instructions file published in the GitHub repository fortrabbit/agent-skills (4 stars, last pushed yesterday), licensed MIT. It adds 605 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
OpenSail AGENTS.md
AGENTS.md instructions for TesslateAI/OpenSail, covering opensail, what is opensail?, architecture overview, technology stack and key code paths.
pinme AGENTS.md
Instructions for glitternetwork/pinme, covering agents.md, project overview, build & dev, architecture and key patterns.
mcp-ssh-manager CLAUDE.md
Claude Code instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.
defang AGENTS.md
AGENTS.md instructions for DefangLabs/defang, covering defang cli agent guide, repository basics, common commands, agent enforcement and go change quality.
moosestack copilot-instructions.md
Instructions for 514-labs/moosestack, covering moose repository guide, code standards, required before each commit, development flow and repository structure.
defang CLAUDE.md
Claude Code instructions for DefangLabs/defang, a project described as: Defang CLI. Develop Once, Deploy Anywhere. Take your app from Docker Compose to a secure and scalable deployment on your favorite cloud in minutes.