vmark: Command for Claude Code

.claude/commands/repo-clean-up.md

repo-clean-up is a command for Claude Code from xiaolai/vmark. It costs 12 tokens per session (294 once invoked), scanned A, original, ISC.

A command that removes failed or canceled GitHub Actions workflow runs and deletes remote branches other than main. GitHub Actions is GitHub's system for running automated checks and builds.

In plain words
What is it for?
Use it for repository maintenance after abandoned work, failed builds, canceled runs, or merged branches have accumulated.
Why use it?
It clears obsolete CI records and branches that can make a repository harder to maintain. The command also prunes local references to deleted remote branches.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is xiaolai/vmark's own configuration. It tells Claude Code how to work on vmark itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vmark configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xiaolai/vmark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xiaolai/vmark/main/.claude/commands/repo-clean-up.md
Clone the repo
git clone --depth 1 https://github.com/xiaolai/vmark

Made for: Claude Code.

Wrote 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.

agentmods badge for repo-clean-up

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaolai/vmark/repo-clean-up/github.svg)](https://agentmods.dev/commands/xiaolai/vmark/repo-clean-up)
Your own site
<a href="https://agentmods.dev/commands/xiaolai/vmark/repo-clean-up"><img src="https://agentmods.dev/badge/commands/xiaolai/vmark/repo-clean-up/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.

agentmods 80×15 button for repo-clean-up

Your own site · 80×15
<a href="https://agentmods.dev/commands/xiaolai/vmark/repo-clean-up"><img src="https://agentmods.dev/badge/commands/xiaolai/vmark/repo-clean-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00294
Opus 5 $0.00006 $0.00147
Sonnet 5 $0.00002 $0.00059
Haiku 4.5 $0.00001 $0.00029

Measured 9d ago against content hash 21192ad0d719, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

repo-clean-up 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 9d 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.

.claude/commands/repo-clean-up.md · 51 lines

What it actually says

Repository Cleanup

Clean up the remote repository by removing failed CI artifacts and stale branches.

Step 1: Delete Failed GitHub Actions Runs

gh run list --status failure --limit 100 --json databaseId --jq '.[].databaseId'

Delete each run with gh run delete <id>.

Report: Deleted N failed runs.

Step 2: Delete Canceled GitHub Actions Runs

gh run list --status cancelled --limit 100 --json databaseId --jq '.[].databaseId'

Delete each run with gh run delete <id>.

Report: Deleted N canceled runs.

Step 3: Delete Stale Remote Branches

List all remote branches except main:

git fetch --prune
gh api repos/{owner}/{repo}/branches --paginate --jq '.[].name' | grep -v '^main$'

Delete each branch with gh api -X DELETE repos/{owner}/{repo}/git/refs/heads/{branch}.

Report: Deleted N remote branches.

Step 4: Prune Local Tracking References

git fetch --prune

Summary

Report total cleanup: Cleanup complete: N failed runs, N canceled runs, N branches removed.

Changes

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.

  1. 9d ago First seen · 51 lines · 12 tokens per session scan A 21192ad0d719

Subscribe to this mod's changes

repo-clean-up is a command published in the GitHub repository xiaolai/vmark (556 stars, last pushed 2d ago), licensed ISC. It adds 12 tokens to every session and 294 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 2026-08-30.