claude-plugins CLAUDE.md

claude-plugins CLAUDE.md is an instructions file for coding agents from lacolaco/claude-plugins. It costs 1,053 tokens per session, scanned A, original, MIT.

Project instructions for changing the claude-plugins codebase. They define the language to use, the files to update together, and how hook scripts and tests should be handled.

In plain words
What is it for?
Use them when modifying a plugin, its hook scripts, its metadata, its README, or its tests in the claude-plugins project.
Why use it?
They reduce inconsistent changes, such as updating code without updating its version, marketplace entry, or documentation. They also require checking that removed names and old values are gone.

Instructions file

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/lacolaco/claude-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/lacolaco/claude-plugins

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-plugins CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lacolaco/claude-plugins/claude-md.svg)](https://agentmods.dev/instructions/lacolaco/claude-plugins/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lacolaco/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/lacolaco/claude-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,053 This file is loaded in full into every session.
When invoked 1,053 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 $0.01053 $0.01053
Opus 5 $0.00526 $0.00526
Sonnet 5 $0.00211 $0.00211
Haiku 4.5 $0.00105 $0.00105

Measured 4d ago against content hash 7452dd30ef43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-plugins

Language

This is an English-language OSS project. All content — code, documentation, commit messages, PR descriptions, and plugin skill definitions — must be written in English. When porting content from non-English sources, translate it as part of the extraction process.

Plugin Change Checklist

When modifying a plugin's behavior, update ALL of the following in the same commit:

  • {plugin}/scripts/*.sh or other code files
  • {plugin}/.claude-plugin/plugin.json (bump version, update description)
  • .claude-plugin/marketplace.json (mirror version and description)
  • README.md: plugin table row, overview, "How it works", "Configuration", and any other references
  • Grep the repo for hardcoded values related to the change (branch names, defaults, etc.) and update every occurrence
  • After updating, grep the repo for every string the prior version exposed that the new version drops or renames (old version numbers, removed field names, deprecated wording, retired terminology) and confirm zero stale occurrences remain before declaring the commit done. A mechanical stale-string sweep is part of the gate, not an optional check.

Hook Script Conventions

When writing a Claude Code hook script ({plugin}/scripts/*.sh referenced from hooks.json):

  • Confirm the hook input schema (cwd, tool_name, tool_input.*, session_id, hook-event-specific fields) before designing the script.
  • Read stdin once into a variable, then run multiple jq queries via printf '%s' "$input" | jq .... Never let jq consume stdin directly when more than one field may be needed now or later.
  • Resolve repo state with git -C "$cwd" using the cwd field from hook input, not the script's inherited cwd.
  • Implement matching logic inside the script (branch on tool_name, inspect tool_input.command, etc.). Conditional fields like if: on hook entries are not honored by Claude Code.

Plugin Testing

"Tests pass" is a strict statement. It means the production path was executed, not that syntax checks succeeded.

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 1,053 tokens per session scan A 7452dd30ef43

Subscribe to this mod's changes

claude-plugins CLAUDE.md is an instructions file published in the GitHub repository lacolaco/claude-plugins (5 stars, last pushed 8d ago), licensed MIT. It adds 1,053 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

langchain AGENTS.md

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens