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/jl-cmd/claude-dev-env/beat-sheetnpx skills add jl-cmd/claude-dev-env --skill beat-sheetgit clone --depth 1 https://github.com/jl-cmd/claude-dev-envWrote 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.
[](https://agentmods.dev/skills/jl-cmd/claude-dev-env/beat-sheet)<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/beat-sheet"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/beat-sheet.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00066 | $0.00504 |
| Opus 5 | $0.00033 | $0.00252 |
| Sonnet 5 | $0.00013 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
beat-sheet 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 4d 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.
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.
What it actually says
beat-sheet
Write in single-line beats. Make each line one complete thought, under 12 words, with a blank line between lines. Keep it to ten lines, each one covering a new point. Order: situation, problem, fix, how it works. Put any command in its own code fence. Start with one short bold title line. Use plain everyday words a tired reader can skim.
Plain words
Name the real thing first — a file, an image, a control, a screen, a size, an id, a proof. Prefer a word the reader can point at over an abstract one. When a word only makes sense on this project, say what it is in the app or on disk (a Theme Studio control, a package file name).
What the reader gets
Lead with the answer. Put most of the reply on what they asked; keep warnings short. For "what's wrong" or "what's missing", answer in this order: what's wrong, what's missing, what follows. For an explain request, give a short summary unless they ask for more.
Around the work
Before the first tool call, say in one sentence what you'll do. While working, speak up only on an important find or a change of course. When you finish, open with the result — what happened or what you found — then add detail only if it helps.
Job size
Do the job asked, at the size asked. Decide small things yourself; ask only when two readings would change the work. When the ask looks off or a better path is clear, say so in one sentence, then do what was asked. Finish the whole job.
Before sending
Read the reply as someone new to the project. Replace any word that needs a glossary with the thing itself.
Visual beats
Add a visual only when it earns its space beyond what the beats
already show on their own. See reference/visual-beats.md for the
shape picker, the rich setup, and a working example.
What ships with it
1 file 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.
- 4d ago First seen · 55 lines · 66 tokens per session scan A e12d2e2e74e6
beat-sheet is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 504 once invoked, about $0.0003 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.
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…