Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. 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/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/skills/cleanup/SKILL.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/cleanup)<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/cleanup"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/cleanup/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/everyone-needs-a-copilot/claude-copilot/cleanup"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/cleanup.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 | $0.00035 | $0.00246 |
| Opus 5.5 | $0.00014 | $0.00098 |
| Sonnet 5.5 | $0.00007 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Clean up project work
Read and apply Work lifecycle, the canonical procedure and compact record template. Use its finish/cleanup sequence for accumulated clutter, or only the relevant checkpoint for ordinary work. Resolve this reference relative to this installed skill, not a machine-specific source checkout.
Work in the existing task and maintained narrative. Preserve original authority and required assets, measure actual net reduction, and obtain exact destructive approval after recovery preparation. Report retained, consolidated, actually removed and held material distinctly; no archive, summary or inventory alone completes cleanup. Route substantial implementation to the appropriate specialist and independent QA under existing task gates.
Validation Checklist
- Resolve current task authority and source state before trusting a summary.
- Check retained assets, recovery evidence and exact approval before removal.
- Verify net reduction and report unresolved holds using the canonical template.
With the existing task ID in TASK_ID, inspect its live record first:
tc task get "$TASK_ID" --json
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 · 23 lines · 35 tokens per session scan A 324c77a7944e
cleanup is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 246 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 2026-10-17.
Other skills, from other repositories
EngineeringManager
Complete engineering management intelligence — team health, technical leadership, hiring, performance management, roadmap execution, stakeholder management, and the IC-to-manager transition.
OKREngine
Complete OKR operating system — goal architecture, cascade design, scoring cadence, anti-patterns diagnosis, quarterly planning, and integrating OKRs with compensation and performance reviews.
PartnershipIntelligence
Complete strategic partnerships intelligence — partnership strategy, BD deal design, integration partnerships, revenue sharing, OEM/white-label, distribution partnerships, and building a partner ecosystem that compounds.
ProductRoadmapOS
Complete product roadmap operating system — strategy translation, prioritization frameworks, stakeholder alignment, roadmap formats, quarterly planning, and saying no without losing trust.
RemoteTeamCommander
Complete operating system for remote and distributed teams — async communication, time zone equity, virtual culture, performance management at a distance, and preventing remote-class citizens.
SprintMaster
Complete Agile/Scrum/Kanban intelligence — sprint planning, backlog grooming, velocity optimization, retrospective facilitation, estimation techniques, and scaling agile for growing teams.