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/kirkchen/beat/setupnpx skills add kirkchen/beat --skill setupgit clone --depth 1 https://github.com/kirkchen/beatWhat 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 | $0.00022 | $0.01883 |
| Opus 5 | $0.00011 | $0.00941 |
| Sonnet 5 | $0.00004 | $0.00377 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
setup 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Beat configuration in the current project.
<decision_boundary>
Use for:
- Setting up Beat for the first time in a project
- Updating existing Beat configuration (language, testing frameworks, rules)
- Detecting project tech stack and recommending test frameworks
NOT for:
- Editing
beat/config.yamldirectly (just edit the file) - Configuring non-Beat tools or project settings
- Creating changes or writing feature files (use
/beat:design)
Trigger examples:
- "Set up Beat" / "Initialize Beat" / "Configure Beat for this project" / "Update Beat config"
- Should NOT trigger: "edit config.yaml" / "design a feature" / "create a change"
</decision_boundary>
Input: None required. The skill gathers information interactively.
Steps
-
Check if config already exists
Check if
beat/config.yamlexists.- If yes: read it, show current config, ask if user wants to update or keep it
- If no: proceed to creation
-
Check superpowers dependency
Check if the superpowers plugin is available by looking for any
superpowers:*skill in the skill list.If not available:
"Beat works standalone, but is better with superpowers — it provides structured brainstorming, TDD discipline, task decomposition, and git worktree isolation.
Install with:
/plugin marketplace add obra/superpowersWithout it, Beat falls back to simpler built-in flows."
Use AskUserQuestion tool:
- "Install now" -- run the install command
- "Continue without it"
If available: proceed silently.
-
Ask artifact language
Use AskUserQuestion tool:
"What language should Beat use for artifacts (proposals, features, designs, tasks)?"
Provide options:
- "English (en)" -- default
- "繁體中文 (zh-TW)"
- "简体中文 (zh-CN)"
- Other -- let user specify a BCP 47 tag
This sets the
languagefield in config. -
Gather project context and detect tech stack
Use AskUserQuestion tool to ask:
"Describe your project so Beat can tailor its artifacts. Include: tech stack, test framework, and any key conventions."
Provide example options:
- "Let me describe it" -- open-ended input
- "Detect from codebase" -- agent scans package.json, Cargo.toml, go.mod, etc.
If user chooses detection:
- Scan common manifest files for tech stack and primary language
- Look for test configuration (vitest.config, jest.config, pytest.ini, etc.)
- Look for BDD runner configuration (cucumber.js, behave.ini, etc.)
- Look for e2e configuration (playwright.config, cypress.config, etc.)
- Check for linter/formatter configs
- Summarize findings and confirm with user
Record the detected/described tech stack — this informs Step 5 framework recommendations.
-
Configure test frameworks
Based on the tech stack from Step 4, recommend appropriate frameworks.
Step 5a: Ask project type
Use AskUserQuestion tool:
"What type of project is this?"
- "Web app (has UI)" -- needs browser automation for e2e
- "API server" -- needs HTTP client for e2e
- "CLI tool" -- needs process execution for e2e
- "Library / SDK" -- e2e usually not needed, behavior tests suffice
Step 5b: Recommend frameworks using the table below
Cross-reference (language × project type) to recommend a framework pair. Present as defaults the user can accept or customize:
"Based on your stack ({language} + {project type}), recommended test frameworks:
- Behavior tests: {recommendation}
- E2E tests: {recommendation}
Accept defaults or customize?"
Framework recommendation table:
Behavior test frameworks (UT / integration):
Language Primary Alternative TypeScript / JavaScript vitest jest Python pytest pytest-bdd Go go test — Java JUnit TestNG C# xUnit NUnit Ruby RSpec — Rust cargo test —
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 210 lines · 22 tokens per session scan A cf2ab9cff83c
setup is a skill published in the GitHub repository kirkchen/beat (7 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,883 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…