Borrowing it
Nothing to install: this file belongs to P47Phoenix/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.
curl -O https://raw.githubusercontent.com/P47Phoenix/Claude-Plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/P47Phoenix/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/p47phoenix/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/p47phoenix/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/p47phoenix/claude-plugins/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/p47phoenix/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/p47phoenix/claude-plugins/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 | $0.01889 | $0.01889 |
| Opus 5.5 | $0.00756 | $0.00756 |
| Sonnet 5.5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
Claude-Plugins CLAUDE.md scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash: curl, mkdir, git operations, chmod, cat, python, sqlite3 How it starts
The opening of the file, as written. The whole thing — 118 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.
Repository Purpose
A marketplace of Claude Code plugins and skills that extend Claude's capabilities with specialized workflows. Hosted at https://github.com/P47Phoenix/Claude-Plugins.
Plugin Structure
Each plugin lives in its own top-level directory and follows this pattern:
<plugin-name>/ # kebab-case naming required
├── SKILL.md # Primary skill instructions (loaded when skill triggers)
├── LICENSE.txt
├── hooks/ # Event-driven automation (optional)
│ ├── hooks.json # Hook definitions (SessionStart, Stop, PreToolUse, PostToolUse, SubagentStop)
│ └── *.py # Python hook implementation scripts
├── scripts/ # Python implementation scripts (shared utilities)
├── skills/ # Sub-skills (optional)
└── references/ # Supporting documentation and examples
The marketplace registry is at .claude-plugin/marketplace.json. Plugins must be registered there with a unique ID, display name, and description.
Each plugin should include an ARCHITECTURE.md with Mermaid diagrams documenting internal design for contributors.
Available Plugins
| Directory | Purpose | Detail |
|---|---|---|
delivery-team/ |
Full delivery team with 11 skills (orchestrator + 10 workers, 7 hooks) | delivery-team/ARCHITECTURE.md |
hardware-team/ |
Hardware delivery pipeline over kicad-happy: 8 stages, 7 roles, 6 hooks | hardware-team/ARCHITECTURE.md |
agentic-flow-builder/ |
Builds multi-agent workflows using ReAcTree hierarchical decomposition | agentic-flow-builder/ARCHITECTURE.md |
prompt-engineer/ |
Expert LLM prompt optimization | — |
prd-quality-gate-flow/ |
7-gate PRD quality workflow with SQLite persistence | — |
research-agent/ |
Research agent with 5 research types and academic frameworks | — |
mtg-commander/ |
MTG Commander deck builder: synergy-first multi-agent pipeline, Scryfall integration, configurable price goals + adversarial Challenger agents via .mtg-commander.yml |
— |
bible-research/ |
Sermon builder (shortlist → choice → breakdown), pre-delivery verification gate, song/post/transcript claim checker, church-calendar lookups, Bible research (timelines, song-idea lists, word studies, people, themes, church history), idea-review team (isolated personas, facilitated rounds, talk mode): 6 skills, 4 agents, 6 commands, 2 hooks | bible-research/ARCHITECTURE.md, bible-research/DESIGN_NOTES.md |
music-team/ |
Music team: song writing, lyrics, theory, cross-genre adaptation; 7-stage pipeline over 9 skills, 5 agents, 14 scripts (10 stage gates), 3 hook scripts, originality guardrails | music-team/ARCHITECTURE.md |
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.
- 15d ago Changed · +1 lines · +114 tokens per session 31765559a997
- 20d ago Changed · +1 lines · +63 tokens per session b5917a4f2c8d
- 1mo ago Changed · +3 lines · +84 tokens per session 555ff665e3f7
- 2mo ago First seen · 113 lines · 1,628 tokens per session scan A 76906a8993a5
Claude-Plugins CLAUDE.md is an instructions file published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 16d ago), licensed MIT. It adds 1,889 tokens to every session, about $0.0076 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Claude-Plugins CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Claude-Plugins CLAUDE.mdP47Phoenix/Claude-Plugins | Instructions file | 2 | 16d ago | MIT | A | 1,889 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 282k | 3d ago | MIT | A | 4,335 | Codex, OpenCode |