Borrowing it
Nothing to install: this file belongs to imisic/claude-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/imisic/claude-marketplace/main/CLAUDE.mdgit clone --depth 1 https://github.com/imisic/claude-marketplaceWrote 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.
[](https://agentmods.dev/instructions/imisic/claude-marketplace/claude-md)<a href="https://agentmods.dev/instructions/imisic/claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/imisic/claude-marketplace/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/imisic/claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/imisic/claude-marketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
claude-marketplace 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Maintenance contract for this repo. It is not the publishing pipeline (that lives outside this repo); it is the set of invariants that must hold inside it, and the checks that catch a break.
Layout
.claude-plugin/marketplace.json the marketplace manifest, lists every plugin
plugins/<name>/ one installable plugin
.claude-plugin/plugin.json the plugin manifest
README.md repo-facing docs for the plugin
STOREFRONT.md site copy for the ivanmisic.net toolshed page
skills/<skill>/SKILL.md model- or user-invoked skills
commands/<name>.md slash commands
rule-packs/<name>/ drop-in .claude/rules/ files, not plugins
STOREFRONT.md site copy, same role as above
STOREFRONT.md is site copy, not plugin content. The toolshed importer reads it for the page and excludes it from the downloadable bundle. Everything else in a plugin directory ships to whoever installs it, so write it for a stranger.
What must move together
Adding, removing, or renaming a plugin touches four places. Miss one and the break is silent.
plugins/<name>/.claude-plugin/plugin.json, the plugin's own manifest..claude-plugin/marketplace.json, the entry in thepluginsarray. A plugin with a validplugin.jsonbut no marketplace entry is invisible; nothing warns you.README.md, a row in the Plugins table, with its storefront link.plugins/<name>/STOREFRONT.md, the page copy, and a matching toolshed row on the site.
Both manifests carry author, homepage, license, and keywords. Keywords are what plugin directories index on, so a new plugin without them is unlisted everywhere but here.
homepage is the plugin's toolshed detail page, and that URL contains the toolshed row's kind. Change a row's kind on the site and two manifests, a README row, and the plugin's own README link all go stale, with nothing to catch it: claude plugin validate checks the schema, never that the URL resolves. The kind also lives in STOREFRONT.md's front matter, so that is a fifth place. sanitize-public moved from skills to plugins this way, following the same move role-lenses made earlier; both left a redirect behind for the old URL.
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.
- 10d ago First seen · 77 lines · 1,321 tokens per session scan A cc41dc1e9153
claude-marketplace CLAUDE.md is an instructions file published in the GitHub repository imisic/claude-marketplace (2 stars, last pushed 8d ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.
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).
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.