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/shdennlin/agent-plugins/claude-mdgit clone --depth 1 https://github.com/shdennlin/agent-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 | $0.01052 | $0.01052 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
agent-plugins CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A marketplace of Claude Code plugins providing workflow automation for AI coding agents. Four plugins ship in a monorepo with a central marketplace registry.
Architecture
Plugin Component Types
Each plugin lives under plugins/{name}/ and can contain any combination of:
- Commands (
commands/*.md) — Slash commands invoked by users. Parse$ARGUMENTS, show--help, then dispatch to an agent viaTasktool withsubagent_type. - Agents (
agents/*.md) — Autonomous agents with YAML frontmatter (identifier,model,tools,whenToUse). The markdown body is the system prompt. - Skills (
skills/{name}/SKILL.md+ companion agent.md) — Auto-discovered capabilities.SKILL.mddefines metadata; the companion file is the agent prompt template. - Scripts (
scripts/*.sh) — Deterministic shell logic invoked by commands or hooks. Used for argument parsing, env validation, path resolution, state setup. Keeps deterministic work out of agent prompts. See "Where to put logic" below. - Hooks (
hooks/hooks.json+hooks/*.sh, or.claude-plugin/hooks/hooks.json) — Event-driven automation (SessionStart,PreToolUse,PostToolUse,Stop). - Templates (
templates/) — Static content injected by agents (e.g., YAML rules).
Dispatch Pattern
Commands and skills follow the same flow: parse args → validate → cd to git root → dispatch agent via Task tool → report results. The agent prompt template (companion .md in skill directory) is separate from the agent definition (agents/*.md with frontmatter).
Where to put logic (design convention)
Each layer has one responsibility. Do not mix layers — putting deterministic work in agent prompts wastes LLM tokens; putting LLM judgment in scripts is impossible. Follow this table:
| Logic type | Location | Why |
|---|---|---|
| Deterministic prep (arg parsing, env validation, path resolution, mkdir, JSON I/O) | scripts/<name>.sh |
No LLM involvement; independently testable from shell; easy to update without re-tokenizing prompts |
| LLM judgment (synthesis, classification, summarization, theming) | agents/<name>.md body |
This is what LLMs do well — keep their prompts focused on it |
| Session-level persistent state (env vars exported once per session) | hooks/<name>.sh via SessionStart, written to $CLAUDE_ENV_FILE |
Persistent across all commands in the session |
| Orchestration (run script, parse its output, dispatch agent) | commands/<name>.md |
Thin (~30–60 lines); links the script result to the agent dispatch |
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 · 85 lines · 1,052 tokens per session scan A d9d40bbfe1cb
agent-plugins CLAUDE.md is an instructions file published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 1,052 tokens to every session, about $0.0053 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
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.