claude-workflow-v2 CLAUDE.md

claude-workflow-v2 CLAUDE.md is an instructions file for coding agents from CloudAI-X/claude-workflow-v2. It costs 1,032 tokens per session, scanned A, original, MIT.

A set of development instructions for building and maintaining Claude Code extensions.

In plain words
What is it for?
Checking plugin changes, adding agents or skills, registering hooks, following formatting rules, and testing extension behavior.
Why use it?
It provides project rules for validation, file structure, coding style, agents, skills, hooks, and testing.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

About the project

Project Starter is a workflow plugin that equips coding agents with specialized subagents, reusable skills, commands, hooks, and output styles for software projects. It is for developers who want structured assistance with tasks such as planning, debugging, code review, security, and automation across several coding-agent platforms. Catalogue add-ons are components of its own workflow.

CloudAI-X/claude-workflow-v2 · 1,413 stars · on GitHub

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/cloudai-x/claude-workflow-v2/claude-md
Clone the repo
git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2

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.

agentmods badge for claude-workflow-v2 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloudai-x/claude-workflow-v2/claude-md.svg)](https://agentmods.dev/instructions/cloudai-x/claude-workflow-v2/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cloudai-x/claude-workflow-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/cloudai-x/claude-workflow-v2/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,032 This file is loaded in full into every session.
When invoked 1,032 The same file — it is already loaded in full.
Security scan A 1 finding. 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 5.1 $0.01032 $0.01032
Opus 5 $0.00516 $0.00516
Sonnet 5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 5d ago against content hash 34b7ad4881a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-workflow-v2 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Use subprocess.run with timeout
CLAUDE.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Development Guidelines

Team-maintained workflow document. Update frequently with new learnings.

Quick Reference

  • Plugin validation: claude plugin validate
  • Test locally: claude --plugin-dir ./
  • Formatting: Prettier for MD/JSON, Black for Python

Development Workflow

Making Changes

  1. Before editing any file:

    • Run claude plugin validate to ensure current state is valid
    • Check existing patterns in similar files
  2. When adding agents (agents/*.md):

    • Copy structure from agents/orchestrator.md as template
    • Include "PROACTIVELY" in description for auto-triggering
    • Specify tools, model (opus/sonnet/haiku), and skills
    • Test trigger keywords work as expected
  3. When adding skills (skills/*/SKILL.md):

    • Keep under 500 lines for optimal context usage
    • Include trigger keywords in description
    • Make content language-agnostic where possible
  4. When adding hooks (hooks/*):

    • Register in hooks/hooks.json
    • Use ${CLAUDE_PLUGIN_ROOT} for paths
    • Exit codes: 0 = allow, 2 = block with message
    • Test with both success and failure cases
  5. After all changes:

    • Run claude plugin validate
    • Test the specific feature with Claude Code

Code Conventions

Markdown Files

  • Use YAML frontmatter for metadata
  • Consistent heading hierarchy (# > ## > ###)
  • Code blocks with language specifiers

Python Hooks

  • Use #!/usr/bin/env python3 shebang
  • Read input from stdin as JSON
  • Handle all exceptions silently (don't block operations)
  • Use subprocess.run with timeout

JSON Files

  • 2-space indentation
  • No trailing commas
  • Validate syntax before committing

Git Workflow

Commit Messages

Follow Conventional Commits:

feat: add new agent for X
fix: correct hook exit code handling
docs: update README with new feature
chore: bump version to X.Y.Z

Branching

  • main is always deployable
  • Feature branches: feature/description
  • Bug fixes: fix/description

Read the full file on GitHub · 171 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. 5d ago First seen · 171 lines · 1,032 tokens per session scan A 34b7ad4881a6

Subscribe to this mod's changes

claude-workflow-v2 CLAUDE.md is an instructions file published in the GitHub repository CloudAI-X/claude-workflow-v2 (1,413 stars, last pushed 11d ago), licensed MIT. It adds 1,032 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 8,242 tokens

llm-safe-haven CLAUDE.md

Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

kleosrules AGENTS.md

AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.

kleosr/kleosrules · 605 tokens

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens