agentmods.dev

agent-plugins CLAUDE.md

A contributor guide for a collection of independently versioned add-ons for AI coding agents. It explains how add-ons can live in this repository or be linked from another repository.

In plain words
What is it for?
Use it to understand the repository structure, distinguish external and built-in add-ons, and follow the process for creating or updating one.
Why use it?
It tells contributors where marketplace entries and add-on files belong, reducing mistakes when adding or maintaining an add-on.

Instructions file

40 4d ago A scan 3,466 tokens original Apache-2.0
View the source file antonbabenko/agent-plugins
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/antonbabenko/agent-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/antonbabenko/agent-plugins
Per session 3,466 This file is loaded in full into every session.
When invoked 3,466 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 $0.03466 $0.03466
Opus 5 $0.01733 $0.01733
Sonnet 5 $0.00693 $0.00693
Haiku 4.5 $0.00347 $0.00347

Measured yesterday against content hash cef9c89f6c37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-plugins CLAUDE.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.

CLAUDE.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

For End Users: See README.md for installation and usage.

This file is for contributors, maintainers, and skill developers.

What This Is

A hybrid multi-plugin marketplace for AI coding agents. Each plugin is executable documentation (a Claude Code / Agent Skills compatible skill) loaded on demand. Plugins are unrelated and versioned independently.

The manifest at .claude-plugin/marketplace.json lists every plugin. A plugin is either:

  • External — referenced via a GitHub source object. Content, tests, and releases live in that plugin's own repo. This repo only pins a ref.
  • Inline — content lives here under plugins/<name>/ and uses this repo's per-plugin release pipeline.

Repository Structure

agent-plugins/
├── .claude-plugin/marketplace.json     # Claude Code marketplace + plugin entries
├── .agents/plugins/marketplace.json    # Codex/agents mirror (external: url+ref)
├── .kiro/plugins/marketplace.json      # Kiro mirror (pin-sync parity; see note)
├── plugins/                            # Inline plugins only (empty until added)
│   └── .gitkeep
│   └── <inline-plugin>/                # (when added) source dir for the manifest
│       ├── skills/<plugin>/            # Autodiscovered: skills/<name>/SKILL.md
│       │   ├── SKILL.md                # Core skill file — single source of truth
│       │   └── references/             # Reference files loaded on demand
│       ├── POWER.md                    # GENERATED Kiro Power (from SKILL.md), CI-owned
│       ├── tests/                      # Baseline scenarios, rationalization table
│       └── CHANGELOG.md                # Per-plugin changelog (CI-managed)
└── .github/
    ├── scripts/
    │   ├── update_external_plugins.py  # Bumps external pins in all 3 manifests
    │   └── build_power.py              # POWER.md generator (`--check` for CI)
    └── workflows/
        ├── validate.yml                # PR validation (hybrid source-aware)
        └── automated-release.yml       # Per-plugin release (inline plugins only)

Read the full file on GitHub · 283 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. yesterday First seen · 283 lines · 3,466 tokens per session scan A cef9c89f6c37

Subscribe to this mod's changes

agent-plugins CLAUDE.md is an instructions file published in the GitHub repository antonbabenko/agent-plugins (40 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,466 tokens to every session, about $0.0173 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.

agent-pluginsagent-skillsclaude-codecodex-skillskiro-powerskills
Related

Other instructions, from other repositories

agent-skills AGENTS.md

Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.

sayeed1999/agent-skills · 1,146 tokens

geekx-skills AGENTS.md

Instructions for geekjourneyx/geekx-skills, covering 智能体指令, 适用范围, 仓库规则, 技能创建规则 and darwin 审查规则.

geekjourneyx/geekx-skills · 1,157 tokens

repo-docs-skills AGENTS.md

AGENTS.md instructions for YurunChen/repo-docs-skills, covering agent instructions, project shape, change rules and suggested checks.

YurunChen/repo-docs-skills · 351 tokens

skills CLAUDE.md

Claude Code instructions for VapiAI/skills, covering vapi skills, mcp documentation server, available skills, experimental reference workflows and configuration.

VapiAI/skills · 328 tokens

agent-skills CLAUDE.md

Instructions for sayeed1999/agent-skills, covering claude.md, output style, 1. think before code, 2. simplicity and 3. architecture boundaries (clean architecture).

sayeed1999/agent-skills · 1,143 tokens

agent-skills AGENTS.md

AGENTS.md instructions for souljorje/agent-skills, covering agent skills, quick reference, rules and development.

souljorje/agent-skills · 322 tokens