Borrowing it
Nothing to install: this file belongs to evmts/tevm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/evmts/tevm/main/.claude/commands/husky.mdgit clone --depth 1 https://github.com/evmts/tevmWrote 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/commands/evmts/tevm/husky)<a href="https://agentmods.dev/commands/evmts/tevm/husky"><img src="https://agentmods.dev/badge/commands/evmts/tevm/husky/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/commands/evmts/tevm/husky"><img src="https://agentmods.dev/badge/commands/evmts/tevm/husky.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 | $0.00000 | $0.01080 |
| Opus 5.5 | $0.00000 | $0.00432 |
| Sonnet 5.5 | $0.00000 | $0.00216 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
husky 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summary
The goal of this command is to verify the repo is in a working state and fix issues if they exist.
Goals
Run CI checks and fix issues until repo is in a good state and then add files to staging. All commands are run from repo root.
0. Make sure repo is up to date via running pnpm i
- Check that the linter passes by running
pnpm lint - Check that types and build pass by running
pnpm nx run-many --targets=build:types,build:dist,build:app,generate:docs,dev:run,typecheck. If one of the specific commands fail, save tokens via only running that command while debugging - Check that tests pass via running
pnpm nx run-many --target=test:coverageSource the .env file first before running if it exists - Check package.json is sorted via running
pnpm run sort-package-json - Check packages are linted via running
pnpm nx run-many --targets=lint:package,lint:deps - Double check. If you made any fixes run preceeding checks again. For example, if you made fixes on step 3. run steps 1., 2., and 3. again to doublecheck there wasn't a regression on the earlier step.
- Add files to staging with
git statusandgit add. Make sure you don't add any git submodules in thelib/*folders though
Do NOT continue on to the next step until the command listed succeeds. You may sometimes have prompts in between or have to debug but always continue on unless I specifically give you permission to skip a check. Print the list of tasks with a checkmark emoji next to every step that passed at the very end
Protocol when something breaks
Take the following steps if CI breaks
1. Explain why it's broke
- Whenever a test is broken first give think very hard and a complete explanation of what broke. Cite source code and logs that support your thesis.
- If you don't have source code or logs to support your thesis, think hard and look in codebase for proof.
- Add console logs if it will help you confirm your thesis or find out why it's broke
- If you don't know why it's broke or there just isn't enough context ask for help
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.
- 1mo ago First seen · 92 lines · 0 tokens per session scan A cc9f1caecf24
husky is a command published in the GitHub repository evmts/tevm (449 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,080 tokens. 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 commands, from other repositories
speckit.companion.living-coverage
Report living-spec requirement→test coverage — per requirement, whether its coverage tier maps a test (opt-in, read-only, never halts).
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
devkit.typescript.code-review
Provides comprehensive TypeScript monorepo code review for Nx workspaces including NestJS backend, React web, and React Native mobile apps. Use when reviewing architecture, boundaries, security, performance, CI/CD and Nx-specific practices.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
claude-loop
Use a fresh headless Claude session (Fable by default) as an independent reviewer of the whole repo, area by area (or of one branch's diff with --base), fix every real finding with regression tests, and loop until each area comes back clean twice in a row. The /codex-loop pattern on Anthropic usage. Runs autonomously.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.