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 skills/parkerm2/create-claude-workflow/workflow-setupnpx skills add ParkerM2/create-claude-workflow --skill workflow-setupgit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWhat 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 | $0.00043 | $0.02788 |
| Opus 5 | $0.00022 | $0.01394 |
| Sonnet 5 | $0.00009 | $0.00558 |
| Haiku 4.5 | $0.00004 | $0.00279 |
Grade B, and why
workflow-setup scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json`. Add (or merge into) the `hooks` section: How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Setup
First-time project configuration for claude-workflow.
Instructions
Follow this setup flow:
1. Check for existing configuration
Read .claude/workflow.json in the current project root. If it exists, display the current configuration to the user and ask what they would like to change. If it does not exist, proceed with first-time setup.
2. Ask configuration questions
Use the AskUserQuestion tool to ask the following questions one at a time:
Question 1: Project rules file
Where is your project rules file? This is the file that contains coding standards, conventions, and project-specific instructions.
Default:
CLAUDE.md
Question 2: Architecture file
Where is your architecture documentation? This file describes your project structure, key abstractions, and design decisions.
Default:
docs/ARCHITECTURE.md
Question 3: Progress directory
Where should workflow progress files be stored? These track feature implementation state for crash recovery.
Default:
.claude/progress
Question 4: Branching strategy
How should branches be organized for feature work?
Options:
Standard(recommended) —base → feature/<name> → work/<name>/<task>with worktrees for agent isolationFlat—base → <featurePrefix>/<task>, agents work on feature branches directly (no work branches)Custom— provide your own prefix configurationDefault:
Standard
Question 5: Base branch
What is your primary/base branch?
Default:
auto(auto-detects main or master)
Question 6: Agent isolation
How should agents be isolated during parallel work?
Options:
Worktrees(recommended) — each agent gets an isolated git worktree directoryShared directory— all agents share one working directory, switching branches via checkoutDefault:
Worktrees
Question 7: Branch enforcement
How strictly should branch rules be enforced?
Options:
warn(recommended) — show warnings but allow the operationblock— prevent commits/pushes on protected branchesoff— no branch checking at allDefault:
warn
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.
- 2d ago First seen · 362 lines · 43 tokens per session scan B b8c6a3ad2fd6
workflow-setup is a skill published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 2,788 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…