oxygen: Command for Claude Code

.claude/commands/run-agentic-tests.md

run-agentic-tests is a command for Claude Code from oxy-hq/oxygen. It costs 35 tokens per session (1,791 once invoked), scanned A, original, Apache-2.0.

A command for running agentic browser tests with the browser visible and extra debugging output. It can run selected flows or all flows in the project's test suite.

In plain words
What is it for?
It is for running and debugging browser-based end-to-end tests locally or narrowing a run to particular flow names.
Why use it?
It removes manual setup of the matching backend and makes the browser actions and agent reasoning easier to inspect when a test fails.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is oxy-hq/oxygen's own configuration. It tells Claude Code how to work on oxygen itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oxygen configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/oxy-hq/oxygen/main/.claude/commands/run-agentic-tests.md
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/oxygen

Made for: Claude Code.

Wrote 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.

agentmods badge for run-agentic-tests

README.md
[![agentmods](https://agentmods.dev/badge/commands/oxy-hq/oxygen/run-agentic-tests/github.svg)](https://agentmods.dev/commands/oxy-hq/oxygen/run-agentic-tests)
Your own site
<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.

agentmods 80×15 button for run-agentic-tests

Your own site · 80×15
<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>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 422da4cd7276, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/commands/run-agentic-tests.md · 172 lines

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").

Read the full file on GitHub · 172 lines

Changes

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.

  1. 2d ago First seen · 172 lines · 35 tokens per session scan A 422da4cd7276

Subscribe to this mod's changes

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.