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/bryanweaver/claude-agent-kit/team-cleanupnpx skills add bryanweaver/claude-agent-kit --skill team-cleanupgit clone --depth 1 https://github.com/bryanweaver/claude-agent-kitWrote 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/bryanweaver/claude-agent-kit/team-cleanup)<a href="https://agentmods.dev/skills/bryanweaver/claude-agent-kit/team-cleanup"><img src="https://agentmods.dev/badge/skills/bryanweaver/claude-agent-kit/team-cleanup.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 5.1 | $0.00019 | $0.00779 |
| Opus 5 | $0.00010 | $0.00390 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
team-cleanup 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 6d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup — Technical Debt and Refactoring
Improve code quality, performance, and maintainability through targeted refactoring.
Area to clean up: $ARGUMENTS
Execution
With Agent Teams (recommended)
Enable with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Create a team and spawn teammates:
- Create team named
cleanup-<area-slug> - Spawn teammates: shipper, reviewer, full-stack-developer, database-admin (if data layer), documentor
Create the following task list with dependencies:
| # | Task | Owner | Blocked By |
|---|---|---|---|
| 1 | Create branch refactor/<area> from main |
shipper | — |
| 2 | Analyze code for smells, bottlenecks, and refactoring opportunities | reviewer | 1 |
| 3 | Refactor application code based on review findings | full-stack-developer | 2 |
| 4 | Refactor data layer based on review findings (if needed) | database-admin | 2 |
| 5 | Commit refactoring changes | shipper | 3, 4 |
| 6 | Run full test suite and validate | shipper | 5 |
| 7 | Update documentation for refactoring changes | documentor | 6 |
| 8 | Create PR to main with before/after summary | shipper | 6, 7 |
Parallelism: Tasks 3 and 4 can run simultaneously after the review completes.
Without Agent Teams (fallback)
Execute sequentially using the Task tool:
Task(shipper, "Create branch refactor/<area> from main")Task(reviewer, "Analyze $ARGUMENTS for code smells, bottlenecks, refactoring opportunities")Task(full-stack-developer, "Refactor based on review findings: <findings>")Task(database-admin, "Refactor data layer: <findings>")— only if neededTask(shipper, "Commit changes: refactor: <description>")Task(shipper, "Run full test suite, validate no regressions")Task(documentor, "Update docs for refactoring changes in: $ARGUMENTS")Task(shipper, "Create PR to main with before/after summary")
Workflow Diagram
┌─────────┐ ┌──────────┐ ┌──────────────────┐ ┌─────────┐ ┌─────────┐ ┌────────────┐ ┌─────────┐
│ Shipper │────►│ Reviewer │────►│ Full Stack Dev │────►│ Shipper │────►│ Shipper │────►│ Documentor │────►│ Shipper │
│ Branch │ │ Analyze │ │ + DB Admin (||) │ │ Commit │ │ Test │ │ Update Docs│ │ PR │
└─────────┘ └──────────┘ │ Refactor │ └─────────┘ └─────────┘ └────────────┘ └─────────┘
│ └──────────────────┘
[Identify Issues]
[Prioritize]
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.
- 6d ago First seen · 65 lines · 19 tokens per session scan A e4e7c0e5a1a9
team-cleanup is a skill published in the GitHub repository bryanweaver/claude-agent-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 779 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.