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/shousper/claude-kit/setupnpx skills add shousper/claude-kit --skill setupgit clone --depth 1 https://github.com/shousper/claude-kitWhat 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 | $0.00133 | $0.01512 |
| Opus 5 | $0.00067 | $0.00756 |
| Sonnet 5 | $0.00027 | $0.00302 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade B, and why
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.
3. Verify: `story doctor` reports a clean board; `cat .claude/story-workflow.json` matches the approved answers. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Workflow Setup
An interview, then story init writes everything. Never hand-write .claude/story-workflow.json — the CLI owns the format.
Core principle: every answer becomes committed config; the gates you define here are what story done will enforce forever after. Get them runnable, not aspirational.
Preflight
- If
.claude/story-workflow.jsonexists, this is reconfiguration — show the current config and confirm with your human partner before overwriting anything. - Confirm you are at the root of a git repository (
git rev-parse --show-toplevel). The board, worktrees, and locks are all repo-relative.
Interview
One topic at a time. Propose detected defaults; the human confirms or corrects.
1. Merge mode
| Mode | Who integrates | When to pick |
|---|---|---|
self |
The agent merges story/st-<id> into main when gates pass |
Solo, high trust, fastest iteration |
local |
Story parks in-review; human reviews the worktree and merges locally | Solo, human wants eyes on every change |
pr |
Push branch + GitHub PR; humans review/merge on GitHub | Teams ("multiplayer") |
If pr, probe before accepting the answer:
gh auth status # must be logged in
git remote get-url origin # must have a remote
gh repo view --json viewerPermission -q .viewerPermission # must be WRITE or ADMIN
Any probe fails → report exactly which one and what it said, and offer local as the fallback. Never configure pr mode on hope.
2. Gates
Detect the test runner from signature files and PROPOSE a test command gate:
| Signal | Proposed gate command |
|---|---|
bun.lock / bun.lockb |
bun test |
pnpm-lock.yaml |
pnpm test |
yarn.lock |
yarn test |
package-lock.json |
npm test |
Cargo.toml |
cargo test |
go.mod |
go test ./... |
pyproject.toml / pytest.ini |
pytest |
Justfile |
inspect just --list for test/check recipes |
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 · 120 lines · 133 tokens per session scan B 8dd4aece3d45
setup is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 5d ago), licensed MIT. It adds 133 tokens to every session and 1,512 once invoked, about $0.0007 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…