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 skills add wsauret/flywheel --skill typescript-bungit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/typescript-bun)<a href="https://agentmods.dev/skills/wsauret/flywheel/typescript-bun"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/typescript-bun/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wsauret/flywheel/typescript-bun"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/typescript-bun.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00242 |
| Opus 5.5 | $0.00006 | $0.00097 |
| Sonnet 5.5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
typescript-bun 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
TypeScript and Bun
Input: a bounded Flywheel TypeScript change and its module and runtime boundary.
Prefer existing project code, standard runtime features, Bun APIs, and installed dependencies before custom code. Model variants with strict types and discriminated unions. A tool input schema root is always one type: "object" schema with a discriminating enum field for variants, never a oneOf, anyOf, or allOf union, because providers reject a union root. Normalize external variation at the boundary and keep owned state strict. Place code in the owning module and preserve dependency direction. Extract only cohesive reused or independently responsible units. Inject side effects, register new behavior through the owning registry, remove dead exports and forwarding wrappers, and preserve platform process requirements.
Stop when all call sites and registry consumers are wired and assigned verification passes. Return implementation or review decisions, affected files and registrations, type and runtime proof, and compatibility risk. Report unavailable runtime capability, boundary conflict, or impossible platform contract. Never bypass it with any, a barrel, compatibility shim, or raw process launch.
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 · 11 lines · 16 tokens per session scan A b82bed501545
typescript-bun is a skill published in the GitHub repository wsauret/flywheel (19 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 242 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-03.
typescript-bun compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| typescript-bunwsauret/flywheel | Skill | 19 | today | Apache-2.0 | A | 16 | Claude Code, Codex |
| effectlfyxhappy/lfcode | Skill | 2 | 1mo ago | MIT | A | 17 | Claude Code, Codex |
| rust-checkHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 15 | Claude Code, Codex |
| better-t-stackAmanVarshney01/create-better-t-stack | Skill | 5.9k | 14d ago | MIT | A | 149 | Claude Code, Codex |
| buncode-yeongyu/senpi | Skill | 512 | today | MIT | A | 237 | Claude Code, Codex |
| bunj4flmao/agent-skills | Skill | 39 | 4d ago | MIT | A | 148 | Claude Code, Codex |
| verify-languageAurite-ai/agent-verifier | Skill | 44 | 25d ago | MIT | A | 48 | Claude Code |