A cleanup tool for local Git branches whose matching branches were deleted from the remote repository.

Use it after pull requests are merged to identify and safely remove local branches marked as gone; it also supports a dry-run preview.

It removes stale branch references and associated worktrees while checking for uncommitted work or unmerged commits first.

clean-gone — Skill for Claude Code and Codex by rlajous: A cleanup tool for local Git branches whose matching…

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 skills/rlajous/claude-code-commands/clean-gone

Any agent

npx skills add rlajous/claude-code-commands --skill clean-gone

Clone the repo

git clone --depth 1 https://github.com/rlajous/claude-code-commands

Made for: Claude Code, Codex.

Or install git-workflow, the plugin that ships this one along with the rest of its 21 skills, 8 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rlajous/claude-code-commands/clean-gone.svg)](https://agentmods.dev/skills/rlajous/claude-code-commands/clean-gone)

Your own site

<a href="https://agentmods.dev/skills/rlajous/claude-code-commands/clean-gone"><img src="https://agentmods.dev/badge/skills/rlajous/claude-code-commands/clean-gone.svg" alt="Measured on agentmods" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,438 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.

Model	Per session	Once invoked
Fable 5	$0.00065	$0.01438
Opus 5	$0.00032	$0.00719
Sonnet 5	$0.00013	$0.00288
Haiku 4.5	$0.00006	$0.00144

Measured 4d ago against content hash 68fe44a7bcc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-gone 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 4d 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.

skills/clean-gone/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-runtime: follow runtime compatibility for invocation, delegation, configuration precedence, state paths, and permissions.

You are cleaning up local Git branches whose remote tracking branch has been deleted (shown as [gone] by Git), along with any worktrees checked out to them. This is destructive, so it is designed to be safe by default: it never discards uncommitted work or unmerged commits without explicit, informed confirmation. Follow each step in order.

Step 1: Parse Arguments

--dry-run → show exactly what would be removed and stop. In dry-run, make no changes to Git state at all (no fetch/prune, no deletion).

Default (no args): proceed through confirmation (Step 4) before any deletion.

Step 2: Refresh Remote State (skip on `--dry-run`)

Only when NOT --dry-run, prune stale remote-tracking refs so [gone] is accurate:

git fetch --prune

On --dry-run, do NOT run this (it mutates local refs). Use the current tracking state and note in the output that it may be stale — the user can re-run without --dry-run to refresh.
If fetch fails (offline, no remote), warn and continue with the current state.

Step 3: Identify Gone Branches

List local branches whose upstream is marked [gone]:

git for-each-ref --format '%(refname:short) %(upstream:track)' refs/heads \
  | awk '$2 == "[gone]" { print $1 }'

Resolve the protected branches (never delete these) from .git-workflow/config.yaml, then .claude/config.yaml as a legacy read-only fallback, then defaults:

workflow.developmentBranch — default staging
workflow.productionBranch — default main
Also always protect: the current branch (git branch --show-current), and master.

Exclude every protected branch from the deletion list even if it is marked [gone] (a gone staging/main is a config/remote quirk, not a signal to delete it).

Step 4: Assess Safety and Confirm

Read the full file on GitHub · 128 lines

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.

4d ago First seen · 128 lines · 65 tokens per session scan A 68fe44a7bcc0

Subscribe to this mod's changes

clean-gone is a skill published in the GitHub repository rlajous/claude-code-commands (30 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,438 once invoked, about $0.0003 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.

Git and workflow agent-skills ai-agents claude-code codex developer-tools

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens