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/agentic-browser-test/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/agentic-browser-test)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/agentic-browser-test"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/agentic-browser-test/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/agentic-browser-test"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/agentic-browser-test.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 | $0.00162 | $0.07403 |
| Opus 5.5 | $0.00065 | $0.02961 |
| Sonnet 5.5 | $0.00032 | $0.01481 |
| Haiku 4.5 | $0.00016 | $0.00740 |
Grade A, and why
agentic-browser-test 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 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.
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 — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Browser Test Skill
You are the expert covering all four reasons a developer or coding agent interacts with the agentic browser testing system in oxy-hq/oxygen-internal:
- Creating a new flow for a new feature or regression. (
/test-feature) - Updating an existing flow when the product surface changes. (
/agentic-test-add-case) - Maintaining the suite — accepting healing recordings, fixing broken flows, managing cache hygiene, calibrating budgets. (
/fix-agentic-test,/accept-agentic-healing) - Running / debugging a failing flow locally or in CI. (
/run-agentic-tests,/fix-agentic-test)
The dev should never have to learn the YAML schema, what act: / wait_for: / expect: is, how the action cache works, what Tier-1 vs Tier-2 healing means, or which bucket their new flow lands in. You are the abstraction.
Step 0 — Always re-read source of truth (every invocation)
The runtime, schema, and authoring conventions evolve fast. Before writing or repairing any YAML, read these source-of-truth files (this skill is colocated in the same repo, so paths below are repo-relative). Do not cache them across invocations.
Canonical sources (PR #2275 shipped the suite; subsequent commits on main may have evolved the surface):
web-app/tests/agentic/README.md— runner mechanics, step kinds,wait_for:primitives, setup commands, action-cache contract, output format.json-schemas/flow-test.json— schema for.flow.test.yml. Settings keys, enum values, defaults, validation rules.web-app/tests/agentic/canonical-prompts.md— verbatim copy-pasteable step text for cross-flowcache_scope: sharedreuse.web-app/tests/agentic/flows/*.flow.test.yml— every existing flow. Canonical authoring examples.web-app/tests/agentic/flows/_budgets.yml— per-flow cost ceilings. When generating a new flow, add an entry here.web-app/tests/agentic/runner/— runtime source. The authoritative answer to "is this tool / primitive / fixture available?" is intool-registry.ts,fixtures/reset.ts(note:fixtures/is a sibling ofrunner/),cli.ts,action-cache.ts,selectors.ts,healing.ts,lint.ts,secrets.ts..github/workflows/agentic-tests.yaml— reusable agentic-tests matrix (bucket layout, cache key formula,flow_bucketdispatch input).ci.yamlcalls this viaworkflow_calland exposes theagentic_onlyfast-path.internal-docs/agentic-browser-testing-spec.md— implementation deep-dive: runtime A/B verdict, post-A.x optimisations, v2 durability mechanism, cache invalidation taxonomy, steady-state cost model, incident retrospective, dated change log.internal-docs/agentic-browser-testing-team-overview.md— team-facing CI mechanics + cost.
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.
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 · 465 lines · 162 tokens per session scan A bc08ff532091
agentic-browser-test is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 162 tokens to every session and 7,403 once invoked, about $0.0006 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 2026-10-14.
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…