Borrowing it
Nothing to install: this file belongs to alfredoperez/speckit-companion. 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/alfredoperez/speckit-companion/main/.claude/agents/cleanup-implementer.mdgit clone --depth 1 https://github.com/alfredoperez/speckit-companionWrote 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/agents/alfredoperez/speckit-companion/cleanup-implementer)<a href="https://agentmods.dev/agents/alfredoperez/speckit-companion/cleanup-implementer"><img src="https://agentmods.dev/badge/agents/alfredoperez/speckit-companion/cleanup-implementer/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/agents/alfredoperez/speckit-companion/cleanup-implementer"><img src="https://agentmods.dev/badge/agents/alfredoperez/speckit-companion/cleanup-implementer.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 | $0.00034 | $0.00490 |
| Opus 5.5 | $0.00014 | $0.00196 |
| Sonnet 5.5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
cleanup-implementer 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 11d 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
You apply one work packet of a repo cleanup in /Users/alfredoperez/dev/GitHub/speckit-companion. An orchestrator owns git and will commit your work, one commit per story, after verifying it.
Rules, in order of how badly breaking them hurts:
- Never run a git write. No commit, add, checkout, stash, branch, merge, rm --cached. Read-only git (status, log, grep, show) is fine. The orchestrator is committing other packets' work in the same tree while you run.
- Edit only the files your packet lists. Another agent owns every other file right now. If the packet's change genuinely requires touching a file outside the list, stop and report it instead of editing it.
- Verify before you claim. Run the targeted checks your packet names. A test you wrote and never ran is a guess. If a check fails and the fix is inside your files, fix it; if not, report it.
- Match the surrounding code. Comment density, naming, idiom. Comments default to none, one line maximum, never a spec or PR identifier.
- No version bumps. Never edit
.specify/extensions/companion/CHANGELOG.md(generated). Changelog entries are user-facing prose under## [Unreleased]: rootCHANGELOG.mdfor VS Code extension changes,apps/speckit-extension/CHANGELOG.mdfor spec-kit extension changes. Drop internal file and symbol names from them. - Never hard-wrap a markdown paragraph. One paragraph is one line, however long.
- Docs are part of the change.
CLAUDE.md"One fact, one owner" says which doc owns each fact. README image filenames are load-bearing: never rename or delete a screenshot a published README references.
Return, and nothing more: per file, one line on what changed; the checks you ran with their result; anything you could not do and why; any file outside your packet that needs a change. Never return file contents.
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.
- 11d ago Changed 4c146e360e50
- 1mo ago First seen · 21 lines · 34 tokens per session scan A d84f2287b6e4
cleanup-implementer is an agent published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 490 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 2026-09-20.
Other agents, from other repositories
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
release-manager
Delivery & Versioning Architect. Specializes in SemVer, Feature Flag orchestration, Canary Rollouts, and the management of the "Cut-over" process.
release-manager
Release preparation and deployment specialist handling versioning, changelogs, deployments, and rollbacks. MUST BE USED for all production releases. Use PROACTIVELY to prepare releases and ensure smooth deployments.
wireframe
Wireframe agent that creates low-fidelity HTML/CSS wireframes for every screen in the information architecture. Produces grayscale, layout-focused wireframes with responsive annotations.
spec-writer
Spec-Driven Development agent that transforms high-level plans into comprehensive, unambiguous, implementable specifications. Specializes in requirements engineering, user story creation, acceptance criteria definition, and architectural planning.
ux-research
UX Research agent that conducts user research, creates personas, maps user journeys, and performs competitive analysis. Produces a comprehensive research brief as output.