skills AGENTS.md

Repository instructions for creating and updating agent skills, which are reusable guides that teach coding agents repeatable tasks.

In plain words
What is it for?
Use them when adding a skill, editing its instructions, linking references, or updating the repository's skill lists.
Why use it?
They define the required file format, naming, descriptions, size limits, and registration checklist.

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/phrase/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/phrase/skills

Made for: Codex, OpenCode.

Per session 145 This file is loaded in full into every session.
When invoked 145 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 $0.00145 $0.00145
Opus 5 $0.00072 $0.00072
Sonnet 5 $0.00029 $0.00029
Haiku 4.5 $0.00015 $0.00015

Measured yesterday against content hash 6aa1257a29b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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 · 21 lines

What it actually says

Agent Instructions

Skill Structure

skills/<skill-name>/SKILL.md

Creating/Updating Skills

  • Frontmatter --- must be the first line of SKILL.md — no comments before it
  • name field must match the directory name exactly
  • description includes trigger keywords — this is how agents discover the skill
  • Keep SKILL.md under 500 lines; move reference material to references/

Registration Checklist

  1. Create skills/<skill-name>/SKILL.md
  2. Add to README.md Available Skills table (alphabetical)

References

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. yesterday First seen · 21 lines · 145 tokens per session scan A 6aa1257a29b4

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository phrase/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 145 tokens to every session, about $0.0007 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.

Related

Other instructions, from other repositories