Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/plazmodium/odin-workflow/browser-testing-with-devtoolsnpx skills add Plazmodium/odin-workflow --skill browser-testing-with-devtoolsgit clone --depth 1 https://github.com/Plazmodium/odin-workflowWrote 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/plazmodium/odin-workflow/browser-testing-with-devtools)<a href="https://agentmods.dev/skills/plazmodium/odin-workflow/browser-testing-with-devtools"><img src="https://agentmods.dev/badge/skills/plazmodium/odin-workflow/browser-testing-with-devtools.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00303 |
| Opus 5 | $0.00012 | $0.00151 |
| Sonnet 5 | $0.00005 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
browser-testing-with-devtools 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 4d 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.
What it actually says
browser-testing-with-devtools
When To Use
- Building, debugging, or reviewing browser UI.
- Behavior depends on real DOM, network, storage, layout, or browser APIs.
- Tests pass but runtime behavior is uncertain.
Workflow
- Start or locate the app in a browser-capable environment.
- Reproduce the target user flow.
- Inspect visible DOM state and accessibility-relevant markup.
- Check console errors and warnings.
- Check network requests, status codes, payload shape, and failure behavior.
- Check performance signals when the task affects rendering, loading, or interaction speed.
- Capture the evidence needed for the final response.
Anti-Rationalization
| Excuse | Rebuttal |
|---|---|
| "Unit tests passed." | Browser integrations fail in ways unit tests do not cover. |
| "The page loaded once." | Check console, network, and key states before trusting it. |
| "Performance seems fine." | Performance claims require measurement. |
Verification
- Browser flow was exercised or the inability to do so is stated.
- Console and network state were checked when relevant.
- Evidence maps to the acceptance criteria.
Exit Criteria
- Browser behavior is proven by runtime evidence or explicitly marked unverified.
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.
- 4d ago First seen · 43 lines · 23 tokens per session scan A 650fa282db54
browser-testing-with-devtools is a skill published in the GitHub repository Plazmodium/odin-workflow (0 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 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 2026-09-01.
Other skills, from other repositories
macbeth
How to drive macOS apps with Macbeth MCP tools — discovery, locators, actions, menus, screenshots/OCR, handles, and fallbacks.
safari
Navigate, search, click links, read content, and manage tabs in Safari.
electron
Automate Electron apps (Slack, VS Code, Discord, etc.) whose UI is Chromium web content exposed through the Accessibility API.
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 14 tools: SearXNG + Exa AI search, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search, and service health. Trigger…
browser-remote-control
Use when an AI agent needs to automate a real browser through Agent Browser Bridge CLI, including remote Chrome control, page extraction, clicking, typing, navigation, or screenshots.
verify
Drive the running ClawStash app in a real browser to verify UI/UX changes end-to-end. Use after nontrivial frontend changes, before committing — tests and tsc alone have missed lifecycle/timing bugs in this repo before (see MEMORY.md.