agentmods.dev

agent-skills-toolkit

agent-skills-toolkit is a plugin for Claude Code from product-on-purpose/agent-skills-toolkit. Its manifest loads nothing; the 27 skills, 2 commands, 7 agents, 1 hook, 1 plugin it bundles cost 2,078 tokens per session together, scanned A, original, Apache-2.0.

A toolkit and set of rules for creating, checking, managing, and expanding skill libraries for coding agents such as Claude Code and Codex.

In plain words
What is it for?
Use it when building or grading agent skills, creating components for several coding agents, or following the Advanced Skill Library Standard.
Why use it?
It gives teams a shared quality bar for skills, so they can review and maintain them consistently as the library grows.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code; mentions Codex.

not rated 2repo changed 3d ago A scan tokens not measured original Apache-2.0

Good fit Use it when building or grading agent skills, creating components for several coding agents, or following the Advanced Skill Library Standard.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add product-on-purpose/agent-skills-toolkit/plugin install agent-skills-toolkit
View source ↗ product-on-purpose/agent-skills-toolkit product-on-purpose.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkit

Made for: Claude Code.

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 agent-skills-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit/github.svg)](https://agentmods.dev/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit)
Your own site
<a href="https://agentmods.dev/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit"><img src="https://agentmods.dev/badge/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-skills-toolkit

Your own site · 80×15
<a href="https://agentmods.dev/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit"><img src="https://agentmods.dev/badge/plugins/product-on-purpose/agent-skills-toolkit/agent-skills-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 27 skills, 2 commands, 7 agents, 1 hook, 1 plugin cost 2,078 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-skills-toolkit 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 3d 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.

.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "agent-skills-toolkit",
  "version": "1.18.0",
  "description": "Toolkit and Standard for authoring, validating, governing, and scaling cross-agent skill libraries (Claude Code and Codex) to a tiered Bronze/Silver/Gold quality bar. Use when building or grading agent skill plugins, when emitting components for multiple agents, or when adopting the Advanced Skill Library Standard.",
  "license": "Apache-2.0",
  "author": {
    "name": "product-on-purpose"
  },
  "homepage": "https://github.com/product-on-purpose/agent-skills-toolkit",
  "repository": "https://github.com/product-on-purpose/agent-skills-toolkit",
  "keywords": [
    "agent-skills",
    "skills",
    "claude-code",
    "codex",
    "plugin",
    "standard"
  ]
}
Contents

What it installs

The manifest is a name and a version. 27 skills, 2 commands, 7 agents, 1 hook, 1 plugin travel with it, and installing the plugin installs all of them — 2,078 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 3d ago Changed 8b89a043b6d3
  2. 8d ago First seen · 20 lines scan A d9a125ef46aa

Subscribe to this mod's changes

agent-skills-toolkit is a plugin published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agentsClaude Codeagent-skillscodexconformancepluginskills
Related

Other plugins, from other repositories

paperthin

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

LilMGenius/paperthin · not measured

jaiskills

Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, an illustrated Claude Agent SDK wizard, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.

JairoTorregrosa/jaiskills · not measured

context-firewall

Context Firewall: use sub-agents to preprocess large inputs with evidence contracts and low-cost verification.

lollipopkit/cc-plugins · not measured

devloop

Iterate until ready to merge: create branch, fix, commit, open PR, wait for AI review, apply feedback, repeat.

lollipopkit/cc-plugins · not measured

sync-claude-skills-to-codex

Sync Claude Code skills to Codex CLI via symlinks. Share your skill library between both AI coding assistants.

ariccb/sync-claude-skills-to-codex · not measured

meta-harness

Intelligent harness creator for Claude Code. Analyzes any project, selects optimal patterns from a curated library of proven architectures (ECC, gstack, OmO, OMC), and generates tailored agents, skills, hooks, and rules — while auto-checking official features to avoid duplication.

bzantium/meta-harness · not measured