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 OKHP3/skillz --skill okhp3-repl-repo-janitorgit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/okhp3-repl-repo-janitor)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-repl-repo-janitor"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repl-repo-janitor/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/okhp3/skillz/okhp3-repl-repo-janitor"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repl-repo-janitor.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 | $0.00120 | $0.02237 |
| Opus 5 | $0.00060 | $0.01118 |
| Sonnet 5 | $0.00024 | $0.00447 |
| Haiku 4.5 | $0.00012 | $0.00224 |
Grade A, and why
okhp3-repl-repo-janitor 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 11d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-repl-repo-janitor
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
A portable, transferable Agent Skill for one specific and common situation: a single Replit workspace's Git checkout has accumulated stale branches, merged/abandoned pull requests, and inconsistently named files, and the user wants it cleaned up safely. Copy this skill's folder into .agents/skills/ in any Repl to reuse it there.
This is a condensed, Replit-shaped descendant of two broader OverKill Hill P³ skills:
okhp3-repository-janitor(multi-repo branch/PR lifecycle across local mirrors)okhp3-repository-organizer(deep content-first repository classification and scaffolding)
Use this skill instead of those two when the scope is "one Repl, tidy the branches and the names," not a fleet of local clones or a full repository re-architecture.
Safety contract
- Start read-only. Run the bundled audit script or equivalent
git/ghinspection before proposing any change. Never delete a branch, PR, file, or folder during discovery. git fetch --allto refresh remote-tracking refs. Never pass--pruneuntil every stale remote branch has been classified.- Treat "merged into origin/main," "closed pull request," and "abandoned with no PR" as three different facts. Check the actual PR state (via the
git-remoteskill orgh pr view) before recommending deletion — an old branch can still have an open, wanted PR. - A Replit-generated name (
subrepl-*,replit-agent,agent/*) is a hint that the branch may be an ephemeral task-agent artifact, not proof it is safe to delete. Confirm it is merged or explicitly abandoned before including it in the delete list. The current/active branch (checked out, or the one the live agent session is using) is never a deletion candidate. - For naming cleanup, apply the kebab-case default (
references/naming-conventions.md) but respect the documented exceptions: PascalCase React components, camelCase hooks, ALL-CAPS root governance files (README.md,LICENSE,CHANGELOG.md,AGENTS.md, etc.), and files whose name is dictated by a tool or a web standard (package.json,.replit,robots.txt,CNAME, ...). - Renaming a file changes import paths and, if it is web content, deployed URLs. Update every importer in the same change, and never rename a file that is live-linked without a redirect or transition plan.
- Always produce a written plan before touching anything. Wait for the user to say "go" (or otherwise explicitly approve the exact items) before executing.
- Never rewrite
main, force-push, or delete stashes/archive refs without a separately stated and confirmed recovery plan.
What ships with it
2 files 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.
- 11d ago First seen · 119 lines · 120 tokens per session scan A 801d64be7c66
okhp3-repl-repo-janitor is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 2,237 once invoked, about $0.0006 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.
Other skills, from other repositories
release-skills
A release workflow for preparing and publishing a new version of a software project. A release is a named version that may include updated version files, release notes, tags, or a GitHub Release.
pm-release
A release-planning workflow for preparing software to go live, including checks, deployment choices, timing, and rollback conditions.
swe-workflow
Orchestrates the full five-stage flow from raw idea to shipped PR — grill-with-docs → to-prd → to-issues → triage → worktree+planning-with-files. Each stage answers one question (What do I want? / What does done look like? / What are the units of work? / What's actionable? / Build it). Use when the user has an idea…
private-fork-sync
Make a public GitHub fork private and keep it synced with its upstream parent. Use when the user wants to make a fork private, or to pull/sync newer commits from the upstream parent into their fork.
skill-repository-maintainer
A maintenance guide for checking, auditing, and synchronising a Codex Skill repository. It covers package structure, metadata, release boundaries, and differences between the source and installed folders.
git-worktree
Use this skill whenever a task involves running parallel work on a git repository without conflicts — e.g. "fix this bug while I keep working on my feature", "run Claude on two branches at once", "work on this task in isolation", "create a throwaway branch for this experiment", or anything where two agents or sessions…