agentmods.dev

claude-code-plugins AGENTS.md

Repository instructions for a collection of Claude Code plugins, which are add-ons containing commands, agents, skills, and hooks. They describe the marketplace files, plugin layout, validation scripts, and development process.

In plain words
What is it for?
Adding or updating plugins, validating their structure, synchronizing marketplace data, and running the collection’s tests.
Why use it?
They help keep plugin metadata, marketplace listings, generated documentation, and automated checks in sync.

Instructions file for CodexOpenCode

7 26d ago A scan 794 tokens original MIT
View the source file DropFan/claude-code-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/dropfan/claude-code-plugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/DropFan/claude-code-plugins

Made for: Codex, OpenCode.

Per session 794 This file is loaded in full into every session.
When invoked 794 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 $0.00794 $0.00794
Opus 5 $0.00397 $0.00397
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00079 $0.00079

Measured yesterday against content hash ef6d9a2e0978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-plugins 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Plugins Collection

This is a Claude Code plugin marketplace repository.

Repository Structure

.claude-plugin/
  marketplace.json      # Marketplace manifest, declares all available plugins
plugins/
  <plugin-name>/        # Self-developed plugin directory
    .claude-plugin/
      plugin.json       # Plugin metadata
    commands/            # User-invokable slash commands
    agents/              # Subagent definitions
    skills/              # Skill modules
    hooks/               # Hook configurations
scripts/
  sync-plugins.sh       # Sync plugin.json metadata to marketplace.json and README.md
  validate-plugins.sh   # Validate plugin structure and metadata (plugin.json, frontmatter, naming)
  verify-sync.sh        # Detect drift between plugin.json and marketplace.json (--run-sync to fix)
  lark-rebuild.py       # Rebuild the lark plugin from lark-cli skill sources
tests/
  run-tests.sh          # Automated test runner
  *-manual-tests.md     # Manual test checklists per plugin
.github/workflows/
  ci.yml                # CI: validate-plugins + verify-sync + tests

Plugin Management

  • Self-developed plugins — Source code lives directly under plugins/<name>/
  • Curated plugins — Referenced in marketplace.json via GitHub source pointing to external repos

Development Guidelines

Adding a Self-developed Plugin

  1. Create a plugin directory under plugins/
  2. Create .claude-plugin/plugin.json with metadata (this is the single source of truth)
  3. Add an entry to the plugins array in marketplace.json with a relative path as source
  4. Run bash scripts/sync-plugins.sh to auto-sync metadata to marketplace.json and README.md

Note: plugin.json is the single source of truth for self-developed plugins. Do NOT manually edit plugin metadata in marketplace.json or README.md — run the sync script instead. The sync covers the description, version, author, keywords, and license fields; other fields are not propagated.

Read the full file on GitHub · 89 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 · 89 lines · 794 tokens per session scan A ef6d9a2e0978

Subscribe to this mod's changes

claude-code-plugins AGENTS.md is an instructions file published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 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.

Code reviewTestingai-codingai-coding-assistantclaude-codeclaude-code-pluginsclaude-code-plugins-marketplaceclaude-code-skills
Related

Other instructions, from other repositories

moo.md CLAUDE.md

Instructions for saadshahd/moo.md, covering claude.md, what this is, conventions, philosophy and model-judgment boundaries.

saadshahd/moo.md · 1,016 tokens

director-mode-lite copilot-instructions.md

Instructions for claude-world/director-mode-lite: This is a Shell/Markdown toolkit for Claude Code Director Mode. Keep shell scripts POSIX-compatible where possible. Markdown files are the primary deliverable.

claude-world/director-mode-lite · 30 tokens

Codelens-AI CLAUDE.md

Instructions for Akshat2634/Codelens-AI, covering claude.md — codelens-ai, project overview, tech stack, project structure and data flow.

Akshat2634/Codelens-AI · 4,204 tokens

agents-plugins AGENTS.md

Instructions for CitiesSkylinesModding/agents-plugins, covering agents.md, project overview, tech stack, repository structure and commands.

CitiesSkylinesModding/agents-plugins · 3,456 tokens

dotclaude CLAUDE.md

Instructions for JHostalek/dotclaude: Treat these instructions as binding user-level invariants, not suggestions or style preferences.

JHostalek/dotclaude · 155 tokens

codeframe AGENTS.md

AGENTS.md instructions for frankbria/codeframe: The guidelines for this repo live in CLAUDE.md. Read that file.

frankbria/codeframe · 145 tokens