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 commands/xbim08/awesome-claude-code-plugins/huskygit clone --depth 1 https://github.com/xbim08/awesome-claude-code-pluginsWrote 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/xbim08/awesome-claude-code-plugins/husky)<a href="https://agentmods.dev/commands/xbim08/awesome-claude-code-plugins/husky"><img src="https://agentmods.dev/badge/commands/xbim08/awesome-claude-code-plugins/husky.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 | $0.00033 | $0.00266 |
| Opus 5 | $0.00016 | $0.00133 |
| Sonnet 5 | $0.00007 | $0.00053 |
| Haiku 4.5 | $0.00003 | $0.00027 |
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 today.
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
Repository Health Verification Protocol
This command outlines a comprehensive protocol for verifying and maintaining a repository's health.
Key Goals
- Verify repo is in a working state
- Run CI checks
- Fix any identified issues
- Prepare files for staging
Main Steps
- Update dependencies with
pnpm i - Run linter checks
- Verify builds and types
- Run test coverage
- Sort package.json
- Lint packages
- Double-check all previous steps
- Stage files (avoiding git submodules)
Error Handling Protocol
- Explain why something broke
- Propose and implement a fix
- Check for similar issues elsewhere
- Clean up debugging code
Important Guidelines
- Never commit, only stage files
- Run tests package-by-package
- Be willing to make necessary fixes
- Use typescript and tests as safeguards
The document emphasizes a methodical approach to maintaining code quality and resolving issues systematically.
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.
- today First seen · 40 lines · 33 tokens per session scan A a31682f6e312
husky is a command published in the GitHub repository xbim08/awesome-claude-code-plugins (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 266 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
commit
Based on the above changes, create a single git commit.
commit-push-pr
Commit, push, and open a PR.
debate
The debate — Claude and Codex argue a design decision from opposite corners, you arbitrate.
remember
Save the current session to persistent context memory.
decide
Forces structured decision-making and creates an auditable Agent Decision Record (AgDR).