stale-forks

stale-forks is a skill for Claude Code from lexfrei/ccc. It costs 102 tokens per session (1,102 once invoked), scanned A, original, BSD-3-Clause.

A cleanup command that finds personal Git forks with no unique work left in them. It can remove their local clones and, after separate confirmation, delete the GitHub forks.

In plain words
What is it for?
Use it to scan repositories, report which forks are obsolete, approve local cleanup, and optionally remove the corresponding GitHub forks.
Why use it?
It helps identify repositories that take up space or create clutter after their changes have already reached the upstream project.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the cleanup plugin — 6 skills shipped together

Good fit Use it to scan repositories, report which forks are obsolete, approve local…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lexfrei/ccc/stale-forks
View source ↗ lexfrei/ccc
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.

Any agent
npx skills add lexfrei/ccc --skill stale-forks
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc

Made for: Claude Code.

Or install cleanup, the plugin that ships this one along with the rest of its 6 skills.

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 stale-forks

README.md
[![agentmods](https://agentmods.dev/badge/skills/lexfrei/ccc/stale-forks.svg)](https://agentmods.dev/skills/lexfrei/ccc/stale-forks)
Your own site
<a href="https://agentmods.dev/skills/lexfrei/ccc/stale-forks"><img src="https://agentmods.dev/badge/skills/lexfrei/ccc/stale-forks.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,102 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 $0.00102 $0.01102
Opus 5 $0.00051 $0.00551
Sonnet 5 $0.00020 $0.00220
Haiku 4.5 $0.00010 $0.00110

Measured 7d ago against content hash e0c237133dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stale-forks 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 7d 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/cleanup/skills/stale-forks/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find personal forks that are no longer useful and reclaim their space.

Operates in report → confirm → execute order. After approval, remove the local clones autonomously. Deleting the GitHub fork is a separate interactive confirmation (it is irreversible and outward-facing). Choices are gathered through interactive questions, not flags.

Step 0: Determine the scan scope (never hardcode paths)

  1. A path in $ARGUMENTS → use it.
  2. Otherwise infer the hosting root by walking up from the current directory to the common clone root, and ask the user to confirm or correct it (interactive question).
  3. If unresolved → ask for the directory to scan. Do not assume a default.

Enumerate repositories under the resolved root (each .git directory).

Step 1: Identify personal forks

Determine the authenticated user once: gh api user --jq .login$ME.

A repository is a personal fork when:

  • it has an upstream remote (git -C "$REPO" remote get-url upstream succeeds), or
  • gh repo view --json isFork,parent,owner,nameWithOwner (run inside the repo) reports isFork == true and owner.login == $ME.

Skip anything that is not a personal fork. Record the upstream nameWithOwner and default branch for each fork.

A fast inventory shortcut for many forks: gh repo list "$ME" --fork --limit 300 --json name,parent,defaultBranchRef, then intersect with local clones present under the root.

Step 2: Assess usefulness

Removing a local clone while keeping the GitHub fork is reversible (re-clone later), so the only irrecoverable risk is local-only work. Check it first, cheaply, with no network:

  • Dirty — uncommitted changes (git status --porcelain non-empty) → keep, flag it.
  • Local-only commits — commits on any local branch not present on any remote: git -C "$REPO" log --oneline --branches --not --remotes. Non-empty → keep, flag it (removing the clone would lose them).

Then assess whether the fork itself is still useful (this is what makes it a candidate, vs just reclonable):

Read the full file on GitHub · 69 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.

  1. 7d ago First seen · 69 lines · 102 tokens per session scan A e0c237133dd6

Subscribe to this mod's changes

stale-forks is a skill published in the GitHub repository lexfrei/ccc (10 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 102 tokens to every session and 1,102 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens