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.
git clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/clean-repo.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/clean-repo.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/clean-repo.eval/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/davistroy/claude-marketplace/clean-repo.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/clean-repo.eval.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 | $0.00488 |
| Opus 5 | $0.00000 | $0.00244 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
clean-repo.eval 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /clean-repo
Purpose
Performs repository cleanup: removes stale files, organizes structure, refreshes documentation. This is a potentially destructive command. Evals should be run in a throwaway clone.
Fixtures
None — operates on the real repository. Always run in a git-cloned scratch copy, never on the working repo.
Setup
git clone <marketplace-repo> /tmp/eval-clean-repo-test
cd /tmp/eval-clean-repo-test
# Add some deliberate stale artifacts for testing:
mkdir -p tmp/ && touch tmp/scratch.txt
touch orphaned-note.txt
Test Scenarios
S1: Standard cleanup run
Invocation: /clean-repo
Must:
- Presents a summary of what will be cleaned before making changes
- Identifies obviously stale files (files in
tmp/, zero-byte files, etc.) - Asks for confirmation before deleting anything
- Does not delete files that are referenced in CLAUDE.md, plugin.json, or marketplace.json
Should:
- Identifies the orphaned-note.txt as a candidate for review
- Reports what was cleaned and what was skipped
- Checks for outdated documentation references
Must NOT:
- Delete plugin command or skill files without explicit confirmation
- Delete git history or .git directory contents
- Modify plugin.json or marketplace.json during cleanup
S2: Dry-run mode (if supported)
Invocation: /clean-repo --dry-run (or equivalent preview)
Must:
- Reports what would be cleaned without making changes
- Output clearly indicates "no changes made"
S3: Cleanup on already-clean repo
Invocation: /clean-repo (on repo with no stale artifacts)
Must:
- Reports "nothing to clean" or equivalent
- Does not error or make unnecessary changes
Rubric
| Criterion | Pass Threshold |
|---|---|
| Preview before changes | Required |
| Confirmation required before destructive actions | Required |
| No deletion of active plugin files | Required |
| Clear post-cleanup summary | Should |
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.
- 12d ago First seen · 77 lines · 0 tokens per session scan A c841fde5332f
clean-repo.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 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
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
handoff
Export a Waybill Bundle by default, or import one when requested.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.