okhp3-repository-janitor

okhp3-repository-janitor is a skill for Codex from OKHP3/skillz. It costs 99 tokens per session (1,236 once invoked), scanned A, original, MIT.

A safety-focused tool for comparing multiple local Git repositories with their GitHub copies. Git is the system that records code changes, while GitHub hosts shared copies and collaboration records.

In plain words
What is it for?
Use it to inventory checkouts, compare them with origin/main, recover local-only work, classify branches and pull requests, and decide what can safely be merged or removed.
Why use it?
It helps find differences between computers and repositories without accidentally deleting uncommitted work, branches, stashes, or hard-to-recover commits.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to inventory checkouts, compare them with origin/main, recover local-only work, classify branches and pull requests, and decide what can safely be merged or removed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okhp3/skillz/okhp3-repository-janitor
View source ↗ OKHP3/skillz
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 OKHP3/skillz --skill okhp3-repository-janitor
Clone the repo
git clone --depth 1 https://github.com/OKHP3/skillz

Made for: Codex.

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 okhp3-repository-janitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repository-janitor/github.svg)](https://agentmods.dev/skills/okhp3/skillz/okhp3-repository-janitor)
Your own site
<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-repository-janitor"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repository-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.

agentmods 80×15 button for okhp3-repository-janitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-repository-janitor"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repository-janitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,236 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 $0.00099 $0.01236
Opus 5 $0.00049 $0.00618
Sonnet 5 $0.00020 $0.00247
Haiku 4.5 $0.00010 $0.00124

Measured 11d ago against content hash 5a5d1a14705f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

okhp3-repository-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_mirrors.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/okhp3-repository-janitor/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

okhp3-repository-janitor

OverKill Hill P³ · overkillhill.com · github.com/OKHP3

Keep a multi-repository Git estate understandable without losing work. Treat origin/main as the comparison baseline, not as evidence that other work is disposable.

Safety contract

  1. Begin with a read-only inventory. Do not delete repositories, branches, stashes, refs, or commits during discovery.
  2. Preserve before pruning. Record dirty files, stashes, local-only commits, and unreachable commits. Pin unreachable commits under a dated refs/archive/ namespace before a later cleanup can trigger garbage collection.
  3. Refresh remotes with git fetch origin; do not use --prune until stale remote branches have been classified.
  4. Compare each checkout to the refreshed origin/main. Report both file-level and commit-level differences.
  5. Treat a merged branch, a closed pull request, and an abandoned branch as different facts. Query the pull request before deletion.
  6. Merge only a reviewed pull request whose checks and destination are suitable. Do not merge a branch merely because it is old or has a bot name.
  7. Delete a remote branch only when its merged/superseded status, commit reachability, and pull-request state are confirmed. Delete the local tracking branch only after the remote deletion is verified.
  8. Never rewrite main, force-push, or remove stashes, archive refs, or untracked files without a separately stated and confirmed recovery plan.

Audit workflow

  1. Resolve the mirror root and verify that every child is a Git checkout. Keep repositories outside that root out of scope.
  2. Run scripts/audit_mirrors.py <mirror-root> --include-unreachable for a read-only baseline. Add --fetch to refresh remote-tracking refs without changing any working tree.
  3. For each repository, inspect the report sections in this order:
    • dirty working-tree files and stashes;
    • commits reachable locally but not from a remote;
    • current HEAD versus origin/main, distinguishing its direct tree difference from the files changed on the branch since the shared base;
    • local and remote branches and whether each is already reachable from origin/main;
    • archive refs and unreachable commits.
  4. Query GitHub for every non-main remote branch: its pull request, whether it is open, closed, or merged, its checks, and whether a newer branch supersedes it. Read references/branch-lifecycle.md before classifying candidates.
  5. Produce a decision ledger with one row per candidate: keep, review, merge, close PR, archive, or delete. State the evidence and recovery point.
  6. Execute in small batches. For each approved merge, refresh, verify the expected head, merge through the pull request, refetch, then delete only the exact verified merged branch. Re-run the audit after every batch.

Read the full file on GitHub · 81 lines

Files

What ships with it

3 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.

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. 11d ago First seen · 81 lines · 99 tokens per session scan A 5a5d1a14705f

Subscribe to this mod's changes

okhp3-repository-janitor is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,236 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

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.

JimLiu/baoyu-skills · 87 tokens

pm-release

A release-planning workflow for preparing software to go live, including checks, deployment choices, timing, and rollback conditions.

konglong87/superPM · 60 tokens

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…

soulmachine/skills · 126 tokens

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.

soulmachine/skills · 47 tokens

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.

ooooooooooooooooooop/agent-tools · 84 tokens

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…

siva01c/claude-plugins · 132 tokens