agentmods.dev

skills AGENTS.md

Repository instructions for packaging the WIO testing workflow as plugins and skills for coding assistants. They list the official locations for plugin files, guidance, scripts, hooks, agents, and marketplace metadata.

In plain words
What is it for?
Use them when maintaining the WIO workflow, editing its testing guidance, updating plugin or marketplace files, or working with its reminder hooks and helper agents.
Why use it?
They prevent duplicate or misplaced files and keep testing guidance in one maintained source while preserving existing reference material.

Instructions file for CodexOpenCode

159 1mo ago A scan 565 tokens original MIT
View the source file workersio/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/workersio/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/workersio/skills

Made for: Codex, OpenCode.

Per session 565 This file is loaded in full into every session.
When invoked 565 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 $0.00565 $0.00565
Opus 5 $0.00282 $0.00282
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00056 $0.00056

Measured 2d ago against content hash 460d1e945d01, 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 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 · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository packages the wio testing workflow skill and plugin for Codex, Claude Code, and other coding agents.

Canonical Paths

  • Plugin: plugins/wio
  • Skill source: plugins/wio/skills/wio/SKILL.md
  • References: plugins/wio/skills/wio/references/
  • Hook script: plugins/wio/skills/wio/scripts/test-review-reminder.py
  • Claude plugin manifest: plugins/wio/.claude-plugin/plugin.json
  • Claude marketplace: .claude-plugin/marketplace.json
  • Claude plugin subagents: plugins/wio/agents/
  • Claude project subagents: .claude/agents/ when copied for project-local use
  • Claude hooks: .claude/settings.json
  • Codex plugin manifest: plugins/wio/.codex-plugin/plugin.json
  • Codex marketplace: .agents/plugins/marketplace.json
  • Codex subagents: .codex/agents/
  • Codex hooks: .codex/hooks.json

Maintenance Rules

  • Do not remove existing reference context.
  • Keep plugins/wio/skills/wio/SKILL.md concise and route detailed testing guidance through plugins/wio/skills/wio/references/index.md.
  • Keep plugins/wio/skills/wio as the source of truth for WIO workflow and testing references.
  • Keep test review strict: low-value tests should be marked REDO or REMOVE, not accepted for coverage.
  • When adding a reference topic, add both overview.md and tools.md, then link it from the WIO reference index.
  • Do not create separate scan, test, workload, review, or doctor skills. They are command modes inside the single wio skill.
  • Do not duplicate references under plugin, cloud, Claude, command, hook, or subagent folders.
  • Subagents may inspect, challenge, and review, but the main agent writes tests and applies the final KEEP, REDO, or REMOVE decision.
  • Claude Code plugins discover Markdown subagents from the plugin root agents/ directory; project-local Claude Code discovers them from .claude/agents/.
  • Codex discovers TOML custom agents from .codex/agents/. Codex plugins do not replace that project custom-agent location.
  • Keep marketplace entries in the official host locations: .agents/plugins/marketplace.json for Codex and .claude-plugin/marketplace.json for Claude Code.
  • Keep install instructions in README.md explicit enough that Codex or Claude can run native marketplace/plugin commands and copy host-specific agent files without a helper script.

Read the full file on GitHub · 35 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. 2d ago First seen · 35 lines · 565 tokens per session scan A 460d1e945d01

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository workersio/skills (159 stars, last pushed 1mo ago), licensed MIT. It adds 565 tokens to every session, about $0.0028 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 2026-08-30.

ProductivityTestingagent-skillsclaude-skillscorrectnessverification
Related

Other instructions, from other repositories

rtl-agent-team CLAUDE.md

Instructions for babyworm/rtl-agent-team, covering language rule, important — project identity, why agentic coding for silicon ip, plugin runtime vs. development context (critical) and plugin architecture: dynamic prompt injection.

babyworm/rtl-agent-team · 7,644 tokens

baerly-storage CLAUDE.md

Toolchain, verification matrix, module map, conventions, anti-patterns. The main agent entry point.

Gusto/baerly-storage · 6,924 tokens

hashloom CLAUDE.md

Claude Code instructions for davet47/hashloom, covering working rules for hashloom, git is the user's, scope discipline, hashloom develops on hashloom and definition of done: >5x token reduction.

davet47/hashloom · 1,643 tokens

anatomia AGENTS.md

Instructions for anatomia-dev/anatomia, covering anatomia-workspace, commands and conventions.

anatomia-dev/anatomia · 80 tokens

anatomia CLAUDE.md

Instructions for anatomia-dev/anatomia, a project described as: Spec-driven agent harness for Claude Code and Codex — five-agent pipeline (scope, plan, build, verify, learn) with an auditable proof chain.

anatomia-dev/anatomia · 49 tokens

verilua AGENTS.md

AGENTS.md instructions for cyril0124/verilua, covering agents.md, project map, where to start, generated code and code style.

cyril0124/verilua · 2,900 tokens