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/adambien/airails/agents-mdgit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/agents-md)<a href="https://agentmods.dev/instructions/adambien/airails/agents-md"><img src="https://agentmods.dev/badge/instructions/adambien/airails/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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade B, and why
airails AGENTS.md scanned grade B with 2 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/*/SKILL.md Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSLO https://github.com/AdamBien/airails/releases/download/skills/airails-claude.zip How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installing airails.dev Skills
Instructions for AI agents asked to install, list, or remove the skills in this repository.
A skill is a directory containing a SKILL.md, organized under bce/, java/, web/, and documentation/. Installation means copying the skill directory — preserving its folder name — into the skills directory of the target agent.
Skill Directories per Agent
| Agent | Skills directory |
|---|---|
| claude | ~/.claude/skills |
| vibe | ~/.vibe/skills |
| kiro | ~/.kiro/skills |
| copilot | ~/.copilot/skills |
| codex | ~/.agents/skills |
| goose | ~/.config/goose/skills |
How to Install
Pick the first applicable option:
1. Interactive terminal available (user is driving)
Ask the user to run ./installSkills from the repository root. Do not run it from an agent shell — it requires an interactive terminal (System.console()) and exits with interactive terminal required when stdin is piped or non-TTY.
2. Agent shell (no TTY)
Copy the skill directories directly. From the repository root:
mkdir -p ~/.claude/skills
find . -name SKILL.md -not -path './target/*' | while read f; do
cp -R "$(dirname "$f")" ~/.claude/skills/
done
Replace ~/.claude/skills with the target agent's directory from the table above. Copying overwrites an existing skill of the same name — acceptable, since this repository is the source of truth for these skills.
3. No JDK, no git
Download the per-agent zip from the rolling skills release and unzip into the home directory:
curl -fsSLO https://github.com/AdamBien/airails/releases/download/skills/airails-claude.zip
unzip -o airails-claude.zip -d ~
Each zip contains all skills with the agent's skills directory baked into the entry paths (airails-claude.zip, airails-vibe.zip, airails-kiro.zip, airails-copilot.zip, airails-codex.zip, airails-goose.zip).
Listing and Removing
./installSkills -l needs no TTY — safe to run from an agent shell. It lists all skills available in the repository and all skills installed per agent directory (requires a JDK 25+).
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 · 67 lines · 633 tokens per session scan B 078781937abc
airails AGENTS.md is an instructions file published in the GitHub repository AdamBien/airails (48 stars, last pushed 14d ago), licensed MIT. It adds 633 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
harness-anchor CLAUDE.md
Instructions for Redtropig/harness-anchor, covering harness-anchor — contributor & ai collaborator guidelines, if you are an ai agent editing this plugin, design invariants (do not break), shell hazards no tool in this repo catches and authoring a new skill (when explicitly asked).
-b2b-lead-hunter-skill CLAUDE.md
Instructions for xiongQvQ/-b2b-lead-hunter-skill, covering claude.md, commands and architecture.
agent-teacher AGENTS.md
AGENTS.md instructions for JackyYang258/agent-teacher, covering agentteacher agent guide, project, repository map, commands and bilingual policy.
agent-teacher CLAUDE.md
Claude Code instructions for JackyYang258/agent-teacher, covering agentteacher, before you start, common commands and project-specific hard rules.