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.
npx agentmods add instructions/verygoodplugins/claude-plugins/claude-mdgit clone --depth 1 https://github.com/verygoodplugins/claude-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00717 | $0.00717 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
claude-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 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.
How it starts
The opening of the file, as written. The whole thing — 75 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.
Project Overview
This is a Claude Code plugin marketplace repository. It hosts plugins that extend Claude Code functionality through commands, hooks, skills, and MCP server integrations.
Repository structure:
plugins/<name>/- Individual plugin directories.claude-plugin/marketplace.json- Marketplace registry listing all plugins
Currently contains the automem plugin (persistent memory via AutoMem MCP service). Other plugins (freescout, evernote, toggl, pirsch) are listed as "coming soon" placeholders.
Plugin Architecture
Each plugin follows this structure:
plugins/<name>/
├── .claude-plugin/plugin.json # Plugin manifest (name, version, author, hooks/mcp refs)
├── .mcp.json # MCP server configuration (optional)
├── commands/*.md # Slash command definitions (YAML frontmatter + markdown)
├── hooks/hooks.json # Event hooks (SessionStart, Stop, PostToolUse)
├── scripts/ # Shell/Python scripts for hooks
└── skills/*/SKILL.md # Skill definitions (YAML frontmatter + markdown)
Key Files
Manifest (plugin.json) - Required fields: name, version, description. Optional: hooks, mcpServers (paths to respective JSON files).
Commands - Markdown files with YAML frontmatter containing description. File name becomes command name (e.g., memory-store.md → /memory-store).
Hooks (hooks.json) - Maps events to handlers:
SessionStart- Runs on session beginStop- Runs when conversation endsPostToolUse- Runs after specific tool execution (usematcherfield)
Hooks can be type: "command" (shell scripts) or type: "prompt" (inject text).
Skills (SKILL.md) - YAML frontmatter with name, description, allowed-tools. Body contains detailed instructions.
AutoMem Plugin Details
The automem plugin provides persistent memory across sessions:
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.
- 2d ago First seen · 75 lines · 717 tokens per session scan A fa315843bb17
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository verygoodplugins/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 717 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
moai-cowork AGENTS.md
Instructions for modu-ai/moai-cowork, covering agents.md — standing contract for agents in this repository, 1. evidence and verification claims, 2. git, branches, and the shared checkout, 3. worktrees and 4. how verification is run.
axiom AGENTS.md
Instructions for netopsengineer/axiom, covering agent instructions, scope, repository map, canonical sources and ownership matrix.
gh-review-loop CLAUDE.md
Instructions for OrenAshkenazy/gh-review-loop, covering claude.md, skill.md placement rule, test runner, if installed via homebrew on apple silicon and or run pytest from a virtual environment.
claude-skills CLAUDE.md
Instructions for revenantworks/claude-skills, covering claude.md — claude-skills, layout, commands, the one arming step and hard rules.
backchain-plugins CLAUDE.md
Instructions for backchainai/backchain-plugins, covering claude.md, repository overview, plugins, architecture and key patterns.
swarmery CLAUDE.md
Claude Code instructions for atretyak1985/swarmery, covering claude.md, what this repo is, commands, validate all json manifests and hook behavioral tests.