cleanup

A Git workflow for reviewing and safely removing local branches that have already been merged. Branches are separate lines of development, and pruning removes outdated remote references.

In plain words
What is it for?
Use it to find merged branches, prune stale remote references, review stashes, and prepare safe branch deletions for confirmation.
Why use it?
It reduces local clutter while protecting the main branches and unmerged work. It also checks for unpushed commits and reminds you about saved stash entries.

Command

Install

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.

agentmods
npx agentmods add commands/owainlewis/youtube-tutorials/cleanup
Clone the repo
git clone --depth 1 https://github.com/owainlewis/youtube-tutorials
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00181
Opus 5 $0.00000 $0.00090
Sonnet 5 $0.00000 $0.00036
Haiku 4.5 $0.00000 $0.00018

Measured 3d ago against content hash fd6f67149af7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

tutorials/ai-git-workflow/resources/commands/cleanup.md · 25 lines

What it actually says

Cleanup

Clean up local branches and stale references.

Instructions

  1. Fetch and prune remote references: git fetch --prune
  2. List all local branches: git branch
  3. Identify branches that have been merged into main
  4. Show the list and confirm before deleting anything
  5. Delete confirmed branches: git branch -d <branch>

Rules

  • Only delete branches that have been fully merged
  • Use -d (safe delete), never -D (force delete) unless explicitly asked
  • Never delete main or develop
  • Show the full list of branches to delete and get confirmation first
  • Report how many branches were cleaned up

Also check

  • git stash list — remind the user if they have stashed work
  • Any branches with unpushed commits — warn before suggesting deletion
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. 3d ago First seen · 25 lines · 0 tokens per session scan A fd6f67149af7

Subscribe to this mod's changes

cleanup is a command published in the GitHub repository owainlewis/youtube-tutorials (375 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 181 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 2026-08-30.