agent-skills AGENTS.md

A repository instruction file for AI agents working on a collection of Agent Skills. It explains the project layout, naming rules, supporting files, and editing conventions.

In plain words
What is it for?
Use it as a guide when editing skill instructions, reference documents, helper scripts, plugin files, or installation hooks in the repository.
Why use it?
It gives coding agents the context needed to change skills without breaking their manifests, scripts, hooks, or marketplace metadata.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/steadwing/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/steadwing/agent-skills

Made for: Codex, OpenCode.

Per session 405 This file is loaded in full into every session.
When invoked 405 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00405 $0.00405
Opus 5 $0.00202 $0.00202
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash 4c292cbdcf5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

AGENTS.md · 32 lines

What it actually says

Repository guide for AI agents

This repo packages Agent Skills for Steadwing, an AI Root Cause Analysis platform. The skills let a coding agent self-register with Steadwing and trigger RCA on production errors.

Layout

  • skills/<name>/SKILL.md — the skill manifest and instructions (the entry point an agent reads).
  • skills/<name>/references/ — supporting docs loaded on demand.
  • skills/<name>/scripts/ — helper scripts (e.g. the error-detection hook and its installer).
  • skills.sh.json — registry/grouping metadata for the skills installer.
  • .claude-plugin/plugin.json — Claude Code plugin manifest (identity, version, license).
  • .claude-plugin/marketplace.json — catalog for the self-hosted marketplace.
  • hooks/hooks.json — registers the detection hook for plugin installs. The install_hook.py script covers skills-CLI installs instead; keep the two in sync when the hook path changes.

Conventions

  • SKILL.md frontmatter requires name and description. The description must clearly state when to use the skill — it's how agents decide relevance.
  • Keep SKILL.md focused; push detail into references/.
  • Scripts must be dependency-free (Python 3 stdlib only) and cross-platform where feasible.
  • The detection hook is passive: it surfaces errors and asks; it never calls the Steadwing API or sends data without explicit user confirmation.

Editing a skill

  1. Update skills/<name>/SKILL.md (and references/ as needed).
  2. If you add a skill, list it in skills.sh.json and the README table.
  3. Validate JSON and SKILL frontmatter (CI runs .github/workflows/validate.yml).
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. 2d ago First seen · 32 lines · 405 tokens per session scan A 4c292cbdcf5f

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository steadwing/agent-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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.