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/wake-engineering/ai-plugin/claude-mdgit clone --depth 1 https://github.com/wake-engineering/ai-pluginWhat 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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
ai-plugin 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 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 — 27 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.
Official docs to create plugins: https://code.claude.com/docs/en/plugins
Repository shape
This repo is a Claude/Cursor plugin — declarative, markdown-only content in agents/, commands/, skills/, .claude-plugin/, .cursor-plugin/, assets/. No build step, no compiled artifacts. Internal-only tooling (publish-copy command/rule) lives in tooling/ and is never copied to the marketplace.
- Consumed by Claude Code (
/plugin install wake-storefront) and by Cursor (added as a local plugin directory). - Both Claude and Cursor manifests use the plugin name
wake-storefront. - The Claude marketplace manifest is at
.claude-plugin/marketplace.json(marketplacename: wake-commerce).
Plugin content rules (non-obvious)
These constraints are repeated at the top of skills, agents, and commands and are easy to miss:
- Forbidden in plugin content: any reference to
api.fbits.net(or*.fbits.net). Markdown underskills/,agents/,commands/must point users at the canonical docs sitehttps://wakecommerce.readme.io/docs/schemainstead. - The publish flow (
tooling/commands/publish-copy.md+tooling/rules/publish-copy.mdc) copies a curated subset of the repo to a separate public marketplace repo. Inclusion list:.cursor-plugin/,.claude-plugin/,.mcp.json,skills/,agents/,commands/,assets/,scripts/, plusREADME-publish.md→README.md. Excluded:tooling/,.bmad-core/,.codex/,.specify/,specs/,.publish-config.json, plus anything not derived from a spec. If you add a new skill/agent/command and it isn't spec-derived, it won't be published. README-publish.mdis the marketplace-facing README. The repo-rootREADME.mdis the toolkit version. Keep them in sync where appropriate, but the publish-only sections (e.g. publish-copy docs) stay out ofREADME-publish.md.
Environment
- Platform is Windows 11 with PowerShell as the default shell. Use PowerShell syntax for any inline commands you suggest the user run (
$env:VAR, not$VAR). .mcp.jsonships only thechrome-devtoolsMCP server (required by theweb-performance-auditskill). Other MCP servers (context7, sequential-thinking, etc.) are referenced as optional external tools in some agents but are NOT auto-installed by this plugin — users must add them to their own MCP config if they want them.
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 · 27 lines · 601 tokens per session scan A 2a54c2f9ec56
ai-plugin CLAUDE.md is an instructions file published in the GitHub repository wake-engineering/ai-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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.
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).
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
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
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.