oxygen: Command for Claude Code

.claude/commands/agentic-test-add-case.md

agentic-test-add-case is a command for Claude Code from oxy-hq/oxygen. It costs 26 tokens per session (1,877 once invoked), scanned A, original, Apache-2.0.

A command for adding a new case to an existing automated flow-test file. A flow test checks a repeatable user journey, such as a conversation or app interaction, using shared setup and settings.

In plain words
What is it for?
Use it when a new case is a close variation of an existing flow. Give it the flow file or name and a description of the additional case.
Why use it?
It keeps related test cases together instead of creating duplicate files. Sharing the same target, setup, and test mode makes the test suite easier to maintain.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is npx --yes ajv-cli@latest validate -s ../json-schemas/flow-test.json -d /tmp/flow.json.

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/agentic-test-add-case.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 agentic-test-add-case

README.md
[![agentmods](https://agentmods.dev/badge/commands/oxy-hq/oxygen/agentic-test-add-case/github.svg)](https://agentmods.dev/commands/oxy-hq/oxygen/agentic-test-add-case)
Your own site
<a href="https://agentmods.dev/commands/oxy-hq/oxygen/agentic-test-add-case"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/agentic-test-add-case/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 agentic-test-add-case

Your own site · 80×15
<a href="https://agentmods.dev/commands/oxy-hq/oxygen/agentic-test-add-case"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/agentic-test-add-case.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,877 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 $0.00026 $0.01877
Opus 5.5 $0.00010 $0.00751
Sonnet 5.5 $0.00005 $0.00375
Haiku 4.5 $0.00003 $0.00188

Measured 2d ago against content hash 534d2b59e665, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-test-add-case 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/agentic-test-add-case.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a case to an existing flow

Use when the dev wants a new test case that's a near-sibling of an existing flow's cases — same target:, same backend_mode:, same setup:, same surface — rather than authoring a whole new file. Sharing settings + setup across cases is cheaper to maintain and keeps related coverage in one place.

$ARGUMENTS is parsed as <flow-file> <description>. The flow file is either a path (web-app/tests/agentic/flows/chat-ask.flow.test.yml) or a stem (chat-ask).

This command must be run from the root of an oxy-hq/oxygen-internal checkout.

Steps

1. Resolve the flow file

# If the dev gave a stem, find the file.
if [ ! -f "$FLOW_PATH" ]; then
  FLOW_PATH=$(find web-app/tests/agentic/flows -name "${FLOW_STEM}.flow.test.yml" | head -1)
fi

If the file doesn't exist, tell the dev: "I can't find a flow at <path>. Either give me the full path or use /test-feature to author a new flow." Exit.

2. Re-read source of truth

Always re-read these — they evolve:

  • web-app/tests/agentic/README.md — confirm the schema hasn't drifted.
  • json-schemas/flow-test.json.
  • web-app/tests/agentic/canonical-prompts.md — for cache_scope: shared step text the new case might want to reuse.
  • The full contents of the target flow file (Read) so you preserve its target:, backend_mode:, settings:, and setup: and add a case that's shape-compatible with the existing ones.

3. Check the existing flow's contract

Before adding a case, verify the new case fits:

  • Same target:? If not, the dev probably wants a new flow, not a new case here. Use AskUserQuestion to confirm.
  • Same backend_mode:? Cases inside one flow share the backend boot. Mixing modes inside one flow doesn't work — local-mode and cloud-mode flows are spawned differently by the runner.
  • Same setup state? If the new case needs different setup (a clean test.sql vs a dirty one, a different starting URL, a different demo file to revert via restore_demo_file:), it can't share this flow's setup: block. Tell the dev and route them to /test-feature instead.
  • No name collision? The new case's name: must be unique within the flow.

Read the full file on GitHub · 184 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 · 184 lines · 26 tokens per session scan A 534d2b59e665

Subscribe to this mod's changes

agentic-test-add-case is a command published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 1,877 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.