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/austinfox/claude-plugins/claude-mdgit clone --depth 1 https://github.com/austinfox/claude-pluginsWrote 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/austinfox/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/austinfox/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/austinfox/claude-plugins/claude-md.svg" alt="Measured on agentmods" 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 | $0.00552 | $0.00552 |
| Opus 5 | $0.00276 | $0.00276 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
austinfox-claude-plugins — Development Guide
Project Overview
This is a Claude Code plugin marketplace containing plugins by Austin Fox. Each plugin lives in its own subdirectory under plugins/.
Structure
.claude-plugin/marketplace.json Marketplace catalog (lists all plugins)
plugins/
tax-advisor/ Tax advisor plugin
.claude-plugin/plugin.json Plugin manifest
skills/tax-advisor/ Auto-triggered skill + on-demand federal, state, profile, and international references
commands/tax-advisor.md /tax-advisor slash command with routing logic
agents/ 4 specialized subagents
scripts/ Bootstrap script for IRS, FinCEN, SSA, WA DOR, CA FTB, and Skatteverket sources
tax-knowledge/ Generated knowledge base (gitignored, per-user)
Adding a New Plugin
- Create
plugins/<plugin-name>/with the standard plugin layout (agents/, commands/, skills/) - Add
.claude-plugin/plugin.jsoninside the plugin directory - Add an entry to
.claude-plugin/marketplace.jsonin thepluginsarray - Run
claude plugin validate .to verify
Tax Advisor Plugin
Bootstrap the knowledge base
cd plugins/tax-advisor/scripts && bun install && bun run bootstrap-knowledge.ts
Use --force to re-download. Auto-refreshes every 30 days.
Test locally
claude --plugin-dir plugins/tax-advisor
Then try /tax-advisor or mention taxes in conversation.
Conventions
- Reference documents in
skills/tax-advisor/references/are loaded on-demand — keep them under 500 lines each - Agents use
${CLAUDE_PLUGIN_ROOT}for all paths - All tax figures and material conclusions must cite current primary authority for the relevant tax year
- Strategies are risk-rated: Conservative / Moderate / Aggressive
- Quantify when supported by the user's inputs; never fabricate precision
- Bootstrap URLs break when government sites restructure — update the relevant source group in
bootstrap-knowledge.ts
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 First seen · 67 lines · 552 tokens per session scan A 176513c39ea6
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository austinfox/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 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
soi-mcp CLAUDE.md
Claude Code instructions for mcpwright/soi-mcp, covering soi-mcp — working agreement, non-negotiable policies, layout (mirrors edgar), what soi-mcp does differently from edgar (data layer only) and publishing & the website.
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.
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.
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.
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).