Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/automata-network/agent-skillsnpx agentmods add skills/automata-network/agent-skills/web-test-cleanupWrote 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/automata-network/agent-skills/web-test-cleanup)<a href="https://agentmods.dev/skills/automata-network/agent-skills/web-test-cleanup"><img src="https://agentmods.dev/badge/skills/automata-network/agent-skills/web-test-cleanup/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/automata-network/agent-skills/web-test-cleanup"><img src="https://agentmods.dev/badge/skills/automata-network/agent-skills/web-test-cleanup.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 | $0.00037 | $0.00944 |
| Opus 5.5 | $0.00015 | $0.00378 |
| Sonnet 5.5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade C, and why
web-test-cleanup scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ./test-output/ How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Cleanup
Clean up test sessions by closing browsers, stopping dev servers, freeing ports, and optionally removing test data.
When to Use This Skill
- BEFORE starting new tests - Run without
--keep-datato get a clean slate - AFTER completing tests - Run with
--keep-datato preserve test artifacts for review - When tests are stuck - Kill hanging browser or server processes
- When ports are blocked - Free common dev ports (3000, 5173, 8080, 4200, 4321)
Quick Start
SKILL_DIR="<path-to-this-skill>"
# Full cleanup (removes test-output folder)
$SKILL_DIR/scripts/cleanup.sh
# Keep test data (screenshots, wallet config, etc.)
$SKILL_DIR/scripts/cleanup.sh --keep-data
What Gets Cleaned Up
Dev Server Stopped
- Reads
test-output/.dev-server.jsonto find and stop the dev server process started by web-test - Only kills the specific process we started, NOT other processes on common ports
Processes Killed
- Test browser processes (Chrome/Chromium using test-output profile)
- Browsers using remote-debugging-port 9222
Ports Freed
- The port used by our dev server (as recorded in
.dev-server.json) - Does NOT kill other processes on common ports to avoid affecting unrelated services
State Files Cleaned
.browser-cdp.json- Browser CDP connection info.browser-state.json- Browser state.dev-server.json- Dev server process info
Files Removed (unless --keep-data)
<project-root>/test-output/
├── screenshots/ # Test screenshots
├── chrome-profile/ # Browser state, wallet data
├── extensions/ # Downloaded wallet extensions
├── console-logs.txt # Browser console output
└── test-report-YYYYMMDD-HHMMSS.md # Generated test report (timestamped)
Instructions
Pre-Test Cleanup (Fresh Start)
Before starting a new test session, run full cleanup:
SKILL_DIR="<path-to-this-skill>"
# Kill all processes and remove test data
$SKILL_DIR/scripts/cleanup.sh
What ships with it
1 file 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.
- 2mo ago First seen · 133 lines · 37 tokens per session scan C 8ebc30491089
web-test-cleanup is a skill published in the GitHub repository automata-network/agent-skills (1 stars, last pushed 9mo ago), licensed MIT. It adds 37 tokens to every session and 944 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.