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 bx33661/oh-my-vul --skill using-omvgit clone --depth 1 https://github.com/bx33661/oh-my-vulWrote 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/bx33661/oh-my-vul/using-omv)<a href="https://agentmods.dev/skills/bx33661/oh-my-vul/using-omv"><img src="https://agentmods.dev/badge/skills/bx33661/oh-my-vul/using-omv/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/bx33661/oh-my-vul/using-omv"><img src="https://agentmods.dev/badge/skills/bx33661/oh-my-vul/using-omv.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 | $0.00086 | $0.01619 |
| Opus 5 | $0.00043 | $0.00809 |
| Sonnet 5 | $0.00017 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
using-omv 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-omv
High-quality growth rule for this project: deepen discipline, do not inflate skill count.
This skill is the session bootstrap. Domain work still lives in the omv-find, omv-audit, omv-repro, and omv-report skills. You use those skills inside the process below — you do not invent parallel workflows.
Platform Invocation
Use the invocation form provided by the active agent:
| Platform | Project manager | Focused skill example |
|---|---|---|
| Pi | /skill:omv |
/skill:omv-audit <id> |
| Codex | $omv |
$omv-audit <id> |
| Claude Code | /omv |
/omv-audit <id> |
In the workflow below, /omv-* is shorthand for the matching focused skill on the active platform.
Iron Laws
1. EVIDENCE BEFORE CLAIMS
2. CLI TRUTH BEFORE PROSE
3. PROCESS BEFORE IMPROVISATION
4. PASSIVE RESEARCH ONLY
When This Applies
Invoke before substantive research action if the user is:
- looking for packages to audit, ranking targets, or running
/omv-find - auditing source → sink → guard, or running
/omv-audit - reproducing, reporting, disclosing, or asking “what next”
- about to say a finding is confirmed, report-ready, non-duplicate, or complete
If you are a subagent doing one delegated slice (e.g. only CVSS math), stay in that slice and still refuse to invent evidence.
Default Research Pipeline
Use this order unless the user already has a later-stage artifact and explicitly continues from it:
1. Orient
omv dashboard OR /omv next
If no campaign and user has a target → omv start / campaign init
2. Open the problem (开题) — prefer Attack Surface Cards when a campaign exists
omv campaign surfaces propose <id>
omv campaign surfaces select <id> --cards <id,id>
omv campaign seed <id>
(If no surfaces file, seed uses generic lanes — still candidate-only.)
3. Deepen one hypothesis at a time
/omv-audit <id> → fill Evidence; never invent file:line
/omv-repro <id> → only when observed_result is the blocker
omv findings validate <id> after material edits
4. Gate before report language
omv review <id> --strict
Optional: /omv-critic <id>, /omv-dedup <id>
5. Report only when ready
/omv-report <id> only if review says ready (or user overrides with explicit draft-only ask)
Then provenance / archive only if user wants lifecycle bookkeeping
What ships with it
4 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.
- 10d ago First seen · 150 lines · 86 tokens per session scan A c1beffdacc6a
using-omv is a skill published in the GitHub repository bx33661/oh-my-vul (4 stars, last pushed 21d ago), licensed MIT. It adds 86 tokens to every session and 1,619 once invoked, about $0.0004 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
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
apple-container
Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
elevenlabs
Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.
google-drive
Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive…
outline
Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).