What is ihudak-claude-plugins CLAUDE.md?

Repository instructions for a Claude Code plugin marketplace and its plugin structure.

Working on the ihudak Claude Code plugins repository, including adding plugins and following its file and registration conventions.

They explain where marketplace, plugin, command, agent, hook, skill, and documentation files belong.

How ihudak/ihudak-claude-plugins configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ihudak/ihudak-claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ihudak/ihudak-claude-plugins/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ihudak/ihudak-claude-plugins

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ihudak/ihudak-claude-plugins/claude-md.svg)](https://agentmods.dev/instructions/ihudak/ihudak-claude-plugins/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ihudak/ihudak-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/ihudak/ihudak-claude-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 21,117 This file is loaded in full into every session.

When invoked 21,117 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.21117	$0.21117
Opus 5	$0.10558	$0.10558
Sonnet 5	$0.04223	$0.04223
Haiku 4.5	$0.02112	$0.02112

Measured 3d ago against content hash a8751f785179, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ihudak-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 3d 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 · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this repo is

A public, open-source Claude Code plugin marketplace hosted at github.com/ihudak/ihudak-claude-plugins. Added with claude plugin marketplace add ihudak/ihudak-claude-plugins, after which it appears in that machine's ~/.claude/plugins/known_marketplaces.json as ihudak-plugins. Registration is per-machine — do not assume any given environment has it.

Structure

.claude-plugin/marketplace.json   ← plugin catalog (do not reformat; Claude Code parses it)
plugins/
  <plugin-name>/
    .claude-plugin/plugin.json    ← required: name, description, author
    README.md
    LICENSE
    commands/                     ← slash commands (.md files)
    agents/                       ← subagent system prompts (.md files, YAML frontmatter required)
    hooks/
      hooks.json                  ← hook declarations; use ${CLAUDE_PLUGIN_ROOT} for paths
      *.sh                        ← hook scripts
    skills/                       ← skills (.md files), if any
    references/                   ← vendored reference docs the commands consult
    docs/                         ← human-facing docs tree (index, per-command, reference pages)

Active plugin: dev-workflows

plugins/dev-workflows/ provides twenty-eight slash commands — /implement, /document, /docs-profile, /epics, /release-notes, /vuln, /upgrade, /api-guideline-reviewer, /guideline-reviewer, /idea, /create-prd, /create-ard, /specify, /design, /frames, /feedback, /prompt, /prompt-brainstorm, /prompt-grill-me, /statusline, /ready, /update-prd, /brd-intake, /brd-ground, /brd-split, /brd-interview, /brd-package, and /brd-reconcile — plus thirty-eight reusable subagents, four hooks, and reference docs.

The live dev-workflows workflow relies on a larger set of helper agents and workflow roles; see the taxonomy and workflow map below.

Internal reference convention:

Agents are invoked by subagent_type (<plugin>:<agent>, e.g. dev-workflows:risk-planner) — never by reading the agent file. Claude Code loads the agent body as its system prompt and honours its model: frontmatter.
Inside agent and skill bodies (and hooks.json / MCP / monitor configs), reference bundled files via ${CLAUDE_PLUGIN_ROOT}/.... This variable does NOT expand in slash-command bodies.
Slash commands that need bundled reference content (e.g. model-routing classification) invoke a skill that resolves ${CLAUDE_PLUGIN_ROOT} on their behalf (see the model-routing skill). Do NOT hardcode ~/.claude/plugins/data/...@.../ paths — that directory holds only empty per-plugin state; installed content lives under ~/.claude/plugins/cache/<marketplace>/<plugin>/<version>/.

Read the full file on GitHub · 358 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.

3d ago Changed · +5 lines · +4,109 tokens per session a8751f785179
8d ago First seen · 353 lines · 17,008 tokens per session scan A 489bfd83fd9c

Subscribe to this mod's changes

ihudak-claude-plugins CLAUDE.md is an instructions file published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. It adds 21,117 tokens to every session, about $0.1056 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.

Building agents Claude Code ai-agents ai-code-review claude-code-plugins developer-productivity documentation-automation

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.

vercel/next.js · 7,296 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 · 5,153 tokens

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

ihudak-claude-plugins: Instructions file for Claude Code