Borrowing it
Nothing to install: this file belongs to oxy-hq/oxygen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oxy-hq/oxygen/main/.claude/skills/oxy-run-and-verify/SKILL.mdgit clone --depth 1 https://github.com/oxy-hq/oxygenWrote 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/oxy-hq/oxygen/oxy-run-and-verify)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/oxy-run-and-verify"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-run-and-verify/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/oxy-hq/oxygen/oxy-run-and-verify"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-run-and-verify.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 | $0.00211 | $0.03818 |
| Opus 5.5 | $0.00084 | $0.01527 |
| Sonnet 5.5 | $0.00042 | $0.00764 |
| Haiku 4.5 | $0.00021 | $0.00382 |
Grade A, and why
oxy-run-and-verify scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `just up --no-frontend` | API only, for `curl` checks | How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the stack, sign in as a persona, verify
The loop is always the same, and it never involves --local, hand-started servers, or env edits:
just up— builds, starts, seeds, serves. Idempotent: re-run it after any change.- Read
.oxy-dev/state.json— URLs, pids, log paths, personas, seeded workspace ids. browser_navigatetohttp://127.0.0.1:5173/dev-login?as=<persona>&next=<path>— that one navigation is the whole sign-in.- Look, click, screenshot. Change code. Back to 1 (or nothing, for web-app edits — Vite hot-reloads).
Here vs agentic-browser-test: this skill is for looking at a change once. A regression you want kept belongs in a committed flow under web-app/tests/agentic/flows/; invoke that skill for it.
Running it from Claude Code
- Run
just up/just status/just downwith the Bash sandbox disabled: they need the Docker socket,ps, and to bind ports. Sandboxed, the script exits at once naming the problem. - A cold
just upcan outlast the 10-minute Bash timeout (a ~7 min first build, image pulls, then the seed compiling ~10 workspaces). Run it withrun_in_background: trueand wait for the completion notification. A warm run is mostly the seed step. - The exit code is the contract. On failure the script prints the last 40 log lines and the log path, so read those before retrying anything.
Commands
| Command | Does |
|---|---|
just up |
cargo build -p oxy-server → oxy start --enterprise (Docker Postgres :15432, API :3000, no-auth internal API 127.0.0.1:3001) → oxy seed --workspace-path ./examples --llm-keys (compiles + promotes every seeded workspace; copies env LLM keys into their secrets) → Vite on 127.0.0.1:5173 → writes state.json and prints three ready sign-in links |
just up --no-build |
reuse the existing binary ($OXY_BIN, else target/debug/oxy) |
just up --no-seed |
skip the seed (faster when data and compiled revisions are already there) |
just up --no-frontend |
API only, for curl checks |
just up --restart |
restart backend + Vite even when healthy (after editing .env) |
just up --clean |
wipe the database volumes first (oxy start --clean) |
just status |
pids, /api/ready, Vite + its /api proxy, containers, current log paths. Exits 1 when not serving |
just down / just down --db |
stop backend + Vite / also docker stop the Postgres + ClickHouse containers |
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.
- 2d ago First seen · 149 lines · 211 tokens per session scan A 01f27c7c4704
oxy-run-and-verify is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 211 tokens to every session and 3,818 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…