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-repository-organizergit 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-repository-organizer)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-repository-organizer"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repository-organizer/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-repository-organizer"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-repository-organizer.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 | $0.00127 | $0.03538 |
| Opus 5.5 | $0.00051 | $0.01415 |
| Sonnet 5.5 | $0.00025 | $0.00708 |
| Haiku 4.5 | $0.00013 | $0.00354 |
Grade A, and why
okhp3-repository-organizer 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- okhp3-askjamie-repo-organizer — 94% identical, 51 lines differ
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-repository-organizer
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Profile an existing local Git repository before changing it. Use the evidence in its files, history, and available local viewers to explain what the repository is for, what kind of repository it is, what is missing, and which structure would make it easier to understand and maintain. Keep the target pattern content-first and proportional to the repository rather than forcing an application template.
Scope
| In scope | Out of scope |
|---|---|
| Mixed content repositories containing prompts, notes, research, office files, PDFs, images, or configuration | Replacing a content repository with an invented runtime, package, or deployment architecture |
| Read-only inventory, purpose discovery, classification, naming and folder proposals | Blind bulk renames, deletion, overwrite, deduplication, or history rewriting |
| Selective governance scaffolding and approval-gated Git moves | GitHub pushes, settings changes, issue creation, or publication unless separately authorized |
Inputs and preconditions
Required input is a local repository path, plus the user's authorization level: assess, propose, or execute an already approved move set. Treat an absent or inaccessible path, a non-Git folder, a dirty working tree, missing viewers, and unavailable Git or Python as reportable conditions, not reasons to guess. The workflow remains useful in assessment mode without optional viewers or the bundled script, but it must name the missing evidence and reduce confidence accordingly.
The default decision path is:
assess → read-only inventory and profile
propose → profile, target shape, approval-gated mapping, and verification plan
execute-approved → only the explicitly approved mapping, followed by verification
Never infer execution approval from a request to "clean up," "organize," or "make it consistent."
Operating contract
What ships with it
13 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.
- agents/openai.yaml 281 B
- evals/brand-profile-cases.json 2.3 KB
- evals/evals.json 3.2 KB
- evals/results.md 2.2 KB
- evals/trigger-cases.json 1.9 KB
- references/agent-skills-quality.md 2.4 KB
- references/archetype-rubric.md 3.1 KB
- references/brand-profiles/askjamie.md 1.0 KB
- references/brand-profiles/glee-fully.md 1.1 KB
- references/cross-platform-naming.md 4.3 KB
- references/github-baseline.md 3.6 KB
- references/scaffold-matrix.md 4.0 KB
- scripts/inventory_repo.py 9.6 KB runs code
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.
- 1mo ago Changed · +25 lines 599cad9a5c5a
- 2mo ago First seen · 196 lines · 127 tokens per session scan A d68df0bae404
okhp3-repository-organizer is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 3,538 once invoked, about $0.0005 per session on Opus 5.5. 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.
git-merge
Merge one branch (usually the default branch) into the current branch while preserving local unstaged changes, resolving conflicts by understanding both sides, and catching silent semantic conflicts with the repo's own checks. Trigger on explicit /git-merge, or when the user asks to merge a branch or the default…
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…
git-worktree
Use when the user asks to create, enter/switch to, or remove a git worktree on Windows — makes it under .claude/worktrees/ and provisions a shared nodemodules (junction) and local .env so it runs without a reinstall. Windows + PowerShell only. Trigger on /git-worktree.
github-issue-creator
Create or edit GitHub issues from raw notes, error logs, voice dictation or screenshots, following the repo's issue templates and labels. Use when the user wants an issue drafted, created or updated.