agentmods.dev

skills AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from zaks-io/skills. It costs 911 tokens per session, scanned A, original, MIT.

An instruction guide for a repository that publishes reusable workflow skills for coding agents. It explains the repository layout, shared rules, and required checks.

In plain words
What is it for?
Use it when editing or reviewing skills, agent configuration, workflow documentation, plugin files, or repository guidance.
Why use it?
It gives agents one source of guidance so published skills, adapters, and internal workflow documents stay aligned.

Instructions file for CodexOpenCode

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 3 +1 5d ago A scan 911 tokens original MIT
View the source file zaks-io/skills
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/zaks-io/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/zaks-io/skills

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zaks-io/skills/agents-md.svg)](https://agentmods.dev/instructions/zaks-io/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zaks-io/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zaks-io/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 911 This file is loaded in full into every session.
When invoked 911 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 $0.00911 $0.00911
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 5d ago against content hash 44fedd1d970f, 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 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.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

zaks-io-skills Agent Guide

Purpose

This repo publishes shared workflow skills for engineering agents. The skills help agents set up repo-local workflow config, move issue-tracked work through implementation, review code and PRs, and create or update PRs consistently.

AGENTS.md is the source of truth for agent guidance. Keep CLAUDE.md as a one-line @AGENTS.md import so Claude Code and other agents read the same content.

Map

  • skills/<skill>/SKILL.md: portable skill instructions. Each skill should have one job and one top-level heading.
  • skills/<skill>/agents/openai.yaml: Codex adapter and trigger fixture for the matching skill.
  • .claude-plugin/plugin.json: Claude Code plugin manifest.
  • .agents/: repo-internal runbooks that are not published by skill discovery.
  • agents/<agent>.md: Claude Code sub-agent definitions for the few workflow roles that benefit from isolated context.
  • skills/ziw-setup/references/: templates and contracts used to create downstream docs/agents/workflow/config.md.
  • skills/ziw-code-review/references/: review support material.
  • docs/agent-workflow.md: technical workflow contract, state model, and role split.
  • docs/skill-distribution.md: source-backed policy for project skills, plugins, global installs, lockfiles, and downstream refresh PRs.
  • docs/skill-portfolio.md: publishable skill surface, trim criteria, and keep/remove rationale.
  • docs/agents/workflow/config.md: repo-local workflow lookup table. Read it before running ziw-* workflow skills in this repo.
  • scripts/check-skills.mjs: structural validation and repo invariants.
  • scripts/update-downstream-skills.mjs: discovers downstream skills-lock.json consumers, runs project-scope skill updates, and reports repos needing PRs.
  • scripts/workflow-contract.mjs: pure workflow decision helpers covered by node --test.
  • README.md: user-facing overview, quick start, and install commands.

Repo Rules

  • Add shared skills under skills/ziw-*.
  • Keep repo-internal procedures under .agents/; do not make them publishable skills unless they are meant to ship to downstream repos.
  • Keep runtime-specific metadata minimal. Tool providers, commands, environments, issue tracker states, and deploy rules belong in each downstream repo's docs/agents/workflow/config.md.
  • Preserve support for both Claude and Codex skill types. When adding or changing a skill, keep the portable SKILL.md contract, Claude-compatible frontmatter, and Codex agents/openai.yaml metadata in sync.
  • All published skills are model-invocable in Claude frontmatter and agents/openai.yaml. Invocation selects a workflow; it does not expand the authority granted by the user's request, repo config, production approval, or merge rules.
  • Claude Code sub-agents live only in root agents/, load skill files through ${CLAUDE_PLUGIN_ROOT}, and use model: inherit. Keep them limited to context-heavy delegation roles, not every workflow skill.
  • ziw-code-review is the implicit review gate and runs from clean context, both as the pre-PR gate and in independent/checkpoint mode.
  • Do not add per-skill scripts unless scripts/check-skills.mjs is updated to allow that skill.
  • Update docs/skill-portfolio.md whenever adding, removing, demoting, or merging a publishable skill.

Read the full file on GitHub · 81 lines

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. 5d ago First seen · 81 lines · 911 tokens per session scan A 44fedd1d970f

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository zaks-io/skills (3 stars, last pushed 5d ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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.

agent-workflowsai-agentsclaudecodexissue-triage
Related

Other instructions, from other repositories

mcpx AGENTS.md

AGENTS.md instructions for lydakis/mcpx, covering agents.md, scope, working style, quality gates and architecture boundaries.

lydakis/mcpx · 540 tokens

agentdeck CLAUDE.md

Claude Code instructions for agentdecksdk/agentdeck, covering agentdeck, 1. product philosophy & north star, 2. architecture & layout, 3. engineering & coding standards and 4. verification gate & conventions.

agentdecksdk/agentdeck · 1,435 tokens

ai-maintainer-copilot-skill AGENTS.md

Instructions for yuxiaoji30-lang/ai-maintainer-copilot-skill, covering agents.md, where the skill lives, what this skill is for, hard rules for any agent using this repo and validating changes.

yuxiaoji30-lang/ai-maintainer-copilot-skill · 348 tokens

agentdeck AGENTS.md

AGENTS.md instructions for agentdecksdk/agentdeck: See CLAUDE.md - single source of agent instructions for this repo.

agentdecksdk/agentdeck · 24 tokens

work-skill AGENTS.md

Instructions for xcaeser/work-skill: Read skills/QUALITY.md before changing this project or any nested Work skill. Treat it as the project's quality bar.

xcaeser/work-skill · 1,006 tokens

stephen-claude CLAUDE.md

Instructions for StephenQiu30/stephen-claude, covering claude.md, 核心原则, sdd / tdd / rag 门禁, 唯一交付流程 and 执行流程.

StephenQiu30/stephen-claude · 2,199 tokens