Borrowing it
Nothing to install: this file belongs to hg-pyun/claude-code-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/hg-pyun/claude-code-marketplace/main/CLAUDE.mdgit clone --depth 1 https://github.com/hg-pyun/claude-code-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/hg-pyun/claude-code-marketplace/claude-md)<a href="https://agentmods.dev/instructions/hg-pyun/claude-code-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/hg-pyun/claude-code-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/hg-pyun/claude-code-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/hg-pyun/claude-code-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 | $0.02918 | $0.02918 |
| Opus 5 | $0.01459 | $0.01459 |
| Sonnet 5 | $0.00584 | $0.00584 |
| Haiku 4.5 | $0.00292 | $0.00292 |
Grade A, and why
claude-code-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 8d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-marketplace — Maintainer Guide
Scope. This file is the maintainer's guide to the repository (
hg-pyun-plugins): the catalog, versioning, validation, and the repo-wide authoring conventions a maintainer enforces. It is not a manual for how the plugins operate — that is self-documented in each plugin's source (plugins/<name>/agents/*.md,skills/*/SKILL.md) and the artifact hand-off contract inscripts/validate.sh. Keep plugin-operation detail out of this file.
30-second picture
- What this is:
hg-pyun-plugins, a personal Claude Code plugin marketplace (static GitHub repo, MIT). It ships 3 plugins:buddy— a Socratic "thinking partner": its/socratic-interviewskill asks one question at a time so you make the design decisions yourself.dev-tools— 16 specialist agents (4 lanes: Build/Analysis · Review · Domain · Coordination) + orchestration / review / debugging / git+GitHub skills.linear-tools— focused Linear ticket workflow (/enrich-ticket).
- Where things live: plugin source under
plugins/<name>/; the catalog in.claude-plugin/marketplace.json; the local health gatescripts/validate.sh; the new-plugin scaffold intemplates/plugin/; the local cross-skill hand-off workspace.dt-handoff/<slug>/(gitignored). - Where to go next:
- Maintaining the repo (add / version / validate a plugin, catalog edits) → this file.
- How an agent or skill works → its own source file (
agents/<name>.md,skills/<name>/SKILL.md) — they are self-documenting. - The artifact hand-off contract (descriptor fields, enums,
@handoffblocks,verdict) → the header ofscripts/validate.sh(machine source of truth + human mirror). - Per-plugin maintenance notes → that plugin's
plugins/<name>/CLAUDE.md(thin). - Installing / using as an end user →
README.md(root) andplugins/<name>/README.md.
Directory layout
claude-code-marketplace/
├── .claude-plugin/marketplace.json # Catalog (3 entries)
├── plugins/
│ ├── buddy/ # skills/ (socratic-interview, grok-codebase) README.md CLAUDE.md — Socratic thinking-partner
│ │ └── .claude-plugin/plugin.json
│ ├── dev-tools/ # agents/ (16) commands/ skills/ scripts/ README.md CLAUDE.md
│ │ └── .claude-plugin/plugin.json
│ └── linear-tools/ # commands/ README.md CLAUDE.md
│ └── .claude-plugin/plugin.json
├── scripts/
│ ├── validate.sh # Health gate (default + --descriptors lanes); header = hand-off contract mirror
│ └── test-validate-descriptors.sh # Red test for the descriptors lane
├── templates/plugin/ # Scaffold for new plugins
├── .dt-handoff/<slug>/ # Local hand-off artifact workspace (gitignored; spec/plan/prd/…)
├── CLAUDE.md ← this file # Repository maintainer guide
├── README.md # Marketplace entry doc (external)
└── LICENSE
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.
- 8d ago First seen · 157 lines · 2,918 tokens per session scan A 1fee47a55112
claude-code-marketplace CLAUDE.md is an instructions file published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,918 tokens to every session, about $0.0146 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).
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.
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.