open-plugin CLAUDE.md

Repository guidance for Claude Code, an AI coding assistant, describing an open-source marketplace of extensions and its project structure.

In plain words
What is it for?
It supports work on the V-Bounce software-development workflow, design-thinking document generation, commands, agents, scripts, and shared reference files.
Why use it?
It gives contributors a common view of the project’s components and the decisions behind them, making work across many commands and agents easier to coordinate.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/baodq97/open-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin
Per session 1,710 This file is loaded in full into every session.
When invoked 1,710 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01710 $0.01710
Opus 5 $0.00855 $0.00855
Sonnet 5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured 2d ago against content hash a9cbf0f1ea11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-plugin 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 2d 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 · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

open-plugins — an open-source Claude Code plugin marketplace containing multiple plugins.

Structure

open-plugins/
├── .claude-plugin/
│   └── marketplace.json              # Marketplace manifest (lists all plugins)
├── plugins/
│   ├── vbounce/                      # V-Bounce AI-Native SDLC Orchestrator v5.1
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/
│   │   │   └── vbounce/              # Orchestrator: state machine + contracts + dispatch
│   │   │       ├── SKILL.md
│   │   │       └── references/       # 16 shared reference files
│   │   ├── commands/                  # 8 slash commands
│   │   │   ├── start.md, status.md, approve.md
│   │   │   ├── bugfix.md, hotfix.md, cr.md
│   │   │   └── skip.md, rollback.md
│   │   ├── agents/                   # 12 agents (req, design, impl, review, deploy, KC, trace, 4x QG, testing)
│   │   └── scripts/                  # Utility scripts
│   │       ├── verify_packages.sh
│   │       └── trace-matrix.py
│   ├── design-thinking/              # Design Thinking PRD Generator v1.0
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/
│   │   │   └── design-thinking/      # Orchestrator: state machine + conversation guides
│   │   │       ├── SKILL.md
│   │   │       └── references/       # 10 shared reference files
│   │   ├── commands/                  # 6 slash commands (start, status, approve, revisit, export, handoff)
│   │   └── agents/                   # 6 agents (empathy, define, ideate, prototype, prd, QG)
│   ├── profile-playbook/              # SFIA 9 Profile Playbook (unified, 9 roles)
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/                    # 9 auto-activating skills (1 per role)
│   │   │   ├── sa-playbook/           # Solution Architecture
│   │   │   ├── po-playbook/           # Product Owner
│   │   │   ├── ba-playbook/           # Business Analysis
│   │   │   ├── testing-playbook/      # Testing
│   │   │   ├── pm-playbook/           # Project Management
│   │   │   ├── ea-playbook/           # Enterprise Architecture
│   │   │   ├── cio-playbook/          # CIO / IT Leadership
│   │   │   ├── cto-playbook/          # CTO / Technology Leadership
│   │   │   └── cpo-playbook/          # CPO / Product Leadership
│   │   ├── commands/                  # 5 shared commands (start, assess, coach, next, status)
│   │   └── agents/                    # 2 shared agents (profile-guide, profile-reviewer)
│   ├── skills-ontology/              # Skills Ontology plugin
│   │   ├── .claude-plugin/plugin.json
│   │   ├── commands/
│   │   ├── hooks/
│   │   ├── rules/
│   │   ├── src/
│   │   ├── bin/
│   │   └── test/
│   ├── chom/                         # chom GitHub skill installer v1.0
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/
│   │   │   └── chom/                 # Single chom skill
│   │   │       └── SKILL.md
│   │   └── README.md
│   └── swe-flow/                     # SWE Flow v0.1
│       ├── .claude-plugin/plugin.json
│       ├── skills/
│       │   ├── goal-define/          # Goal structuring skill
│       │   │   ├── SKILL.md
│       │   │   └── references/goal-template.md
│       │   └── domain-decompose/     # DDD domain decomposition (+ delta-merge update mode)
│       │       ├── SKILL.md
│       │       └── references/       # methodology, output-template, 2 canvases
│       └── README.md
├── LICENSE
└── .npmignore

Read the full file on GitHub · 129 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.

  1. 2d ago First seen · 129 lines · 1,710 tokens per session scan A a9cbf0f1ea11

Subscribe to this mod's changes

open-plugin CLAUDE.md is an instructions file published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,710 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories