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 commands/cloudai-x/claude-workflow-v2/tutorialgit clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2What 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 | $0.00023 | $0.01447 |
| Opus 5 | $0.00012 | $0.00724 |
| Sonnet 5 | $0.00005 | $0.00289 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
tutorial 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 yesterday.
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Tutorial
Welcome the user and guide them through the plugin's features interactively. This is a read-only walkthrough -- no files are modified.
Step 0: Detect Context
Before starting, silently gather context:
- Use Glob to find
package.json,pyproject.toml,Cargo.toml,go.mod, or other project markers in the working directory - Identify the project's primary language and framework
- Use Glob to list the plugin's available components:
agents/*.mdfor agentsskills/*/SKILL.mdfor skillshooks/hooks.jsonfor hookscommands/*.mdfor commands
Then begin the tutorial.
Step 1: Meet the Agents
Greet the user and introduce the agent system.
Read each file in agents/*.md and present a summary table:
Welcome to the Claude Workflow Plugin tutorial.
Let's explore what this plugin gives you. First up: Agents.
Agents are specialized assistants that activate automatically based on
your request. Here's what's available:
| Agent | Triggers When You... | Model |
|-----------------|----------------------------------------|--------|
| orchestrator | Need multi-file coordinated changes | opus |
| code-reviewer | Ask for a code review | sonnet |
| debugger | Report a bug or error | sonnet |
| ... | ... | ... |
Agents marked PROACTIVELY in their description will activate
automatically when your prompt matches their trigger keywords.
You don't need to invoke them explicitly.
Explain that the orchestrator can spawn subagents for parallel work, and how agent selection works based on prompt keywords.
Try it: Suggest the user try a prompt like "review the last commit for issues" to see the code-reviewer agent activate.
Step 2: Commands at Your Fingertips
Read the list of command files from commands/*.md and present them:
Commands are slash-invocable workflows. Think of them as recipes
that combine multiple steps into one action.
Available commands:
| Command | What It Does |
|---------------------|-------------------------------------------|
| /project-starter:commit | Auto-generate conventional commit |
| /project-starter:verify-changes | Multi-agent verification suite |
| /project-starter:review | Code review with structured output |
| ... | ... |
Commands can be simple (commit) or complex (verify-changes spawns
5+ parallel subagents).
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.
- yesterday First seen · 190 lines · 23 tokens per session scan A 23b72339f0c8
tutorial is a command published in the GitHub repository CloudAI-X/claude-workflow-v2 (1,411 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 1,447 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
learn
Command "learn" from chohra-med/expo_boilerplate, covering command: learn — the learning loop (feedback → rules), when to run it, invocation, the loop (6 steps) and 1 — capture.
learn
Learn Claude Code best practices and capture lessons into persistent memory.
insights
Surface patterns from your pro-workflow learnings and session history.
learn-rule
Capture a lesson from this session into permanent memory.