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/fix-agentic-test.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/fix-agentic-test)<a href="https://agentmods.dev/commands/oxy-hq/oxygen/fix-agentic-test"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/fix-agentic-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/commands/oxy-hq/oxygen/fix-agentic-test"><img src="https://agentmods.dev/badge/commands/oxy-hq/oxygen/fix-agentic-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 | $0.00039 | $0.02877 |
| Opus 5.5 | $0.00016 | $0.01151 |
| Sonnet 5.5 | $0.00008 | $0.00575 |
| Haiku 4.5 | $0.00004 | $0.00288 |
Grade A, and why
fix-agentic-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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage and repair a failing agentic browser flow
When a flow is failing in CI (or locally), classify the failure into one of four buckets and route the dev to the right fix. Don't guess — the fixes are very different and applying the wrong one can hide a real bug or pay needless re-record cost.
$ARGUMENTS is the flow stem (e.g. chat-ask, builder-edits-app) or
a CI bucket name (builder, semantic, ask-agent, threads, ide, metric-tree).
This command must be run from the root of an oxy-hq/oxygen-internal
checkout.
Steps
1. Sanity-check + locate artefacts
test -f web-app/tests/agentic/README.md || { echo "Not in an oxy-hq/oxygen-internal checkout"; exit 2; }
Find the most recent results files:
RESULTS_DIR=web-app/tests/agentic/.results
LATEST_MD=$(ls -t "$RESULTS_DIR"/*.md 2>/dev/null | head -1)
LATEST_JSON=$(ls -t "$RESULTS_DIR"/*.json 2>/dev/null | head -1)
HEALING="$RESULTS_DIR/healing.json"
STAGING=web-app/tests/agentic/.cache/healing-staging.json
If no results exist locally, the dev probably saw the failure in CI. Two paths:
- Download CI artefacts from the failed run (
agentic-results-<bucket>artifact contains the JSON, markdown summary, traces, and backend logs). - Reproduce locally:
/run-agentic-tests <flow-stem>and continue triage from the local results.
2. Read the latest summary
cat "$LATEST_MD"
In the markdown summary look for:
- The failing case (
❌ <case-name>). - Per-step debug table —
iterations,error,from_cache,selector_drift_eventsfor each step. - Cost-budget warnings (
⚠️ over budget).
3. Classify the failure
Walk through the four buckets in order. First match wins.
Bucket A — Tier-1 self-heal happened (no action needed)
Signal: test passed BUT selector_drift_events > 0 in step_debug
for one or more steps.
What it means: a primary recorded selector failed, a fallback resolved, the cache's strategy ranks updated silently. $0 LLM cost. The test ran clean.
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 · 273 lines · 39 tokens per session scan A ba373ec953f6
fix-agentic-test is a command published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 2,877 once invoked, about $0.0002 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.