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/commands/run-agentic-tests.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/commands/oxy-hq/oxygen/run-agentic-tests)<a href="https://agentmods.dev/commands/oxy-hq/oxygen/run-agentic-tests"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/run-agentic-tests/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/commands/oxy-hq/oxygen/run-agentic-tests"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/run-agentic-tests.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 | $0.00035 | $0.01791 |
| Opus 5.5 | $0.00014 | $0.00716 |
| Sonnet 5.5 | $0.00007 | $0.00358 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
run-agentic-tests 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run agentic browser tests
Wraps pnpm test:agentic with HEADED=1 DEBUG=1 so the dev sees the
browser and the per-iteration LLM reasoning.
The runner auto-spawns the right oxy backend based on each flow's
settings.backend_mode (cloud, the default, → enterprise mode: oxy start --enterprise, oxy seed of demo_project/, and a dev-login session as
[email protected], all on port 3000; local → the legacy oxy start --local --enterprise). No port-probing or pre-start dance needed.
$ARGUMENTS is one or more positional flow-name substring filters
(OR-combined). A flow matches if its filename contains ANY of the listed
substrings. Empty $ARGUMENTS = all flows.
This command must be run from the root of an oxy-hq/oxygen-internal
checkout.
Steps
1. Sanity-check the working directory
test -f web-app/tests/agentic/README.md && test -f json-schemas/flow-test.json
If either path is missing, exit and tell the dev: "This command must be
run from the root of an oxy-hq/oxygen-internal checkout where the agentic
browser-test layer is present (see web-app/tests/agentic/README.md)."
2. Confirm ANTHROPIC_API_KEY is set
The runner exits 2 with ERROR: ANTHROPIC_API_KEY is required if it's
unset (see runner/cli.ts). Fail loudly before spawning anything:
if [ -z "${ANTHROPIC_API_KEY:-}" ]; then
echo "Set ANTHROPIC_API_KEY first: export it, or add to web-app/.env.local."
exit 2
fi
3. Validate Docker is up (the runner needs it for Postgres)
docker info >/dev/null 2>&1 || {
echo "Docker Desktop must be running — \`oxy start\` brings up Postgres in a container."
exit 2
}
4. Run the tests
From web-app/:
cd web-app
HEADED=1 DEBUG=1 pnpm test:agentic $ARGUMENTS
The runner reads each loaded flow's settings.backend_mode (default
cloud, enterprise mode), spawns the right oxy start … invocation and
seeds demo_project/ itself. If a backend is already healthy at the
resolved URL, the runner uses it as-is: no respawn and no seed — a
just up stack has examples/ as its Demo workspace and does not allow
[email protected] to sign in (see the runner README, "Run").
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 · 172 lines · 35 tokens per session scan A 422da4cd7276
run-agentic-tests is a command published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,791 once invoked, about $0.0001 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 commands, from other repositories
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
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.
amazing-e2e-check
Run explicitly requested E2E, browser, device, or installed-deployment scenarios in an independent verification workflow.
verify-pr
Verify a PR's frontend changes through browser automation.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.