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/lhohan/claude-code-plugins/agents-mdgit clone --depth 1 https://github.com/lhohan/claude-code-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 | $0.01819 | $0.01819 |
| Opus 5 | $0.00910 | $0.00910 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This repository contains reusable Claude Code plugins distributed via the hanlho-plugins marketplace. The collection is geared towards architecture, code quality, and development workflow automation.
Current Plugins
- jujutsu-vcs - SessionStart hook for Jujutsu VCS integration
- skill-evaluator - Skill for evaluating Claude Code skills against best practices
- hanlho-cmds - Collection of productivity commands for workflow automation
Plugin Types by Capability
Claude Code plugins can implement four capability types:
Hooks
Automatically execute at lifecycle events (e.g., SessionStart) to inject context.
Example: jujutsu-vcs
jujutsu-vcs/
├── .claude-plugin/plugin.json
├── hooks/hooks.json
├── hooks-handlers/jujutsu-reminder.sh
├── docs/decisions/
└── README.md
Use case: Guaranteed context injection for critical operations (VCS reminders, security guidelines).
Skills
LLM-invoked specialized capabilities for on-demand expertise.
Example: skill-evaluator
skill-evaluator/
├── .claude-plugin/plugin.json
├── skills/skill-evaluator/SKILL.md
├── references/EXAMPLE.md
└── README.md
Use case: Optional, specialized capabilities requiring LLM judgment to activate.
Commands (Slash Commands)
User-triggered workflows via /plugin-name:command-name syntax.
Example: hanlho-cmds
hanlho-cmds/
├── .claude-plugin/plugin.json
├── commands/bbh.md
└── README.md
Use case: Frequently used workflow shortcuts, prompt templates, multi-step procedures.
Agents
Specialized expert personas for task delegation (not yet used in this repository).
Structure: agents/<agent-name>.md with frontmatter defining role, expertise, and model preference.
Use case: Domain-specific expert roles for complex subagent workflows.
Plugin Distribution
Plugins are exposed via .claude-plugin/marketplace.json at the repository root. Each plugin:
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.
- yesterday First seen · 254 lines · 1,819 tokens per session scan A aef8bb70e58e
claude-code-plugins AGENTS.md is an instructions file published in the GitHub repository lhohan/claude-code-plugins (2 stars, last pushed 9mo ago), licensed MIT. It adds 1,819 tokens to every session, about $0.0091 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.