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.
npx skills add ivy00johns/Skill-Madness --skill repo-cleanup-loopgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/skills/ivy00johns/skill-madness/repo-cleanup-loop)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/repo-cleanup-loop"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/repo-cleanup-loop/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/skills/ivy00johns/skill-madness/repo-cleanup-loop"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/repo-cleanup-loop.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 | $0.00203 | $0.02829 |
| Opus 5 | $0.00102 | $0.01414 |
| Sonnet 5 | $0.00041 | $0.00566 |
| Haiku 4.5 | $0.00020 | $0.00283 |
Grade A, and why
repo-cleanup-loop 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-cleanup-loop
A configuration of [
loop-controller]. That skill supplies the loop machinery — primitive selection, the full guardrail stack, state externalization. This skill supplies the three things specific to "keep the repo state intentional": the per-class recipe (it delegates the post-merge-branch case to [git-post-merge-cleanup], it does not re-implement it), the mechanical proof (a classified inventory where nothing is "safely removable" until evidence flips it), and the recover-before-delete HITL boundary that makes deletion safe. Readloop-controllerfor the guardrails; they're inherited, not repeated here.Why
disable-model-invocation: this loop deletes branches, prunes refs, and removes worktrees on its own, on a clock — irreversible acts. It is user-driven: you want to type/loopit weekly (or run/repo-cleanup-looponce), not have Claude silently start pruning because it noticed debris.
The 5-part contract
| Part | This loop |
|---|---|
| trigger | a weekly cadence (/loop or /schedule) over the whole repo, or an explicit /repo-cleanup-loop |
| action | ONE pass: scan repo state (branches + PRs + commits + worktrees) → classify each item → recover anything valuable → remove one class of safely-removable items with evidence → re-scan |
| proof | the repo state is intentional — every branch / PR / worktree is current OR owned OR safely-removed-with-evidence — default-FAIL: each inventory item starts "reviewed": false and only flips on classification + evidence |
| memory | the classified inventory JSON (per-item: kind, name, class, evidence, "reviewed", "recovered"), a recovery log (what was salvaged + where), and git history / reflog as the durable undo trail |
| stop | every item reviewed and intentional (proof) OR iteration/pass cap OR no-progress for 3 passes (same item unresolved) OR budget cap OR an HITL checkpoint on an ambiguous item |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 194 lines · 203 tokens per session scan A 8bdd29b32ae3
repo-cleanup-loop is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 2d ago), licensed MIT. It adds 203 tokens to every session and 2,829 once invoked, about $0.0010 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…