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 dmae97/omk --skill omk-enginegit clone --depth 1 https://github.com/dmae97/omkWrote 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/dmae97/omk/omk-engine)<a href="https://agentmods.dev/skills/dmae97/omk/omk-engine"><img src="https://agentmods.dev/badge/skills/dmae97/omk/omk-engine/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/dmae97/omk/omk-engine"><img src="https://agentmods.dev/badge/skills/dmae97/omk/omk-engine.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 | $0.00044 | $0.01241 |
| Opus 5.5 | $0.00018 | $0.00496 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
omk-engine 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMK Project Engine
Use !skill:omk-engine to run this repository with a small, task-specific OMK profile.
Scope
- Keep the global agent installation at
~/.omk/agentprivate. Do not copy it into this repository or a release artifact. - This repository already discovers global skills and
.omk/skills/; do not duplicate or reinstall an available skill. - Run
omk-initonly for an explicit readiness request. Usebootstrap.mjs --all; reserve--fullfor a complete verification pass.
Select the smallest workflow
Load one primary skill and at most two supporting skills for a task.
| Task | Primary | Supporting |
|---|---|---|
| Codebase search | insane-search |
ast-grep |
| TypeScript, Python, Rust, or Go work | programming |
matching *-patterns skill |
| Small implementation | ponytail |
programming |
| Multi-step, checkable goal | omk-plan |
adaptorch, omk-loop |
| OMK runtime, hooks, MCP, or agent work | omk-engineering |
adaptorch |
| Documentation | docs-write-concisely |
docs-update-docs |
| Significant implementation review | review-work |
remove-ai-slops only for explicit cleanup |
| Browser or desktop task | omk-computeruse |
deterministic browser tools first |
| Authorized reverse-engineering workflow | reverse-skill |
task-specific route only |
Verification-first engineering cycle
This brownfield repository adapts the process discipline from Addy Osmani's
agent-skills at the pinned commit recorded in
SOURCE.md. Do not install the upstream pack wholesale: this runtime already has
colliding engineering skills, and duplicate names make routing less deterministic.
For every non-trivial change:
- Contract — name the requested behavior, boundaries, and observable evidence.
- Characterize — inspect the existing diff and add a failing or behavior-pinning check before changing established code.
- Slice — implement one thin, complete increment. Keep independent lanes parallel and dependency-ordered work sequential.
- Verify — run the narrow test/type/lint gate for the slice; record the exact command and result.
- Doubt — for branching, boundary, concurrency, security, or irreversible decisions, review the smallest artifact against its contract with a fresh, issue-seeking context.
- Stop or escalate — stop when the evidence passes and review finds no substantive new issue. After at most three repair/review cycles, surface unresolved findings instead of grinding indefinitely.
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.
- 1mo ago First seen · 94 lines · 44 tokens per session scan A 39fd63bb4c8c
omk-engine is a skill published in the GitHub repository dmae97/omk (148 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,241 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
money
Skill "money" from Hmbown/Codewhale, covering money, when to use, setup, workflow and non-goals.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
document
Skill "document" from Hmbown/Codewhale, covering document, when to use, non-goals and workflow.
research
Current external research using available web tools, primary sources where possible, links/citations, date awareness, synthesis, and unresolved uncertainty.