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/ss26367098/rawtrace-mcp/rawtrace-debug-browsernpx skills add ss26367098/rawtrace-mcp --skill rawtrace-debug-browsergit clone --depth 1 https://github.com/ss26367098/rawtrace-mcpWrote 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/ss26367098/rawtrace-mcp/rawtrace-debug-browser)<a href="https://agentmods.dev/skills/ss26367098/rawtrace-mcp/rawtrace-debug-browser"><img src="https://agentmods.dev/badge/skills/ss26367098/rawtrace-mcp/rawtrace-debug-browser.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 5.1 | $0.00077 | $0.00918 |
| Opus 5 | $0.00039 | $0.00459 |
| Sonnet 5 | $0.00015 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
rawtrace-debug-browser 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Browser with RawTrace
Use RawTrace to capture evidence that a normal post-action snapshot misses. Follow the workflow below regardless of the client-added MCP namespace; match tools by their final RawTrace tool name.
Decide whether RawTrace applies
Use this skill when the problem depends on browser event ordering or a state transition that is intermittent, transient, or unexplained. Typical signals include:
- A Playwright or Cypress action sometimes fails, passes only with sleeps, or produces different results across runs.
- A click appears to do nothing, sends no expected request, navigates unexpectedly, or has an unclear result.
- DOM content appears and disappears between snapshots, or asynchronous rendering changes the target.
- API requests, redirects, WebSocket messages, downloads, authentication callbacks, or response bodies occur in the wrong order.
- A regular browser snapshot cannot show why the behavior happened.
Do not invoke RawTrace for static styling changes, ordinary code reading or summarization, deterministic unit-test failures with no browser timing component, or simple webpage fact lookup.
Confirm authorization and sensitivity
RawTrace can record raw DOM text, form values, headers, cookies, request and response bodies, WebSocket frames, screenshots, and tokens.
- For an explicitly authorized development or test environment, pass
acknowledgeRawCapture: truedirectly when a RawTrace tool requires it. Do not ask for an additional RawTrace-specific confirmation. - If the target system, account, environment, or data authorization is unclear, ask before capturing raw data.
- Client approval prompts still apply. Never bypass client security settings.
- Do not print whole traces, paste raw secrets into the answer, or commit trace directories or ZIP bundles.
Choose the smallest useful workflow
One uncertain interaction
Prefer browser_observe_action_result for one click, type, press, check, select, hover, scroll, reload, or navigation whose result is unclear. It combines before and after state, DOM, network, and optional screenshot evidence. In an explicitly authorized development or test environment, include acknowledgeRawCapture: true in this call.
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.
- 4d ago First seen · 65 lines · 77 tokens per session scan A c42d78835b69
rawtrace-debug-browser is a skill published in the GitHub repository ss26367098/rawtrace-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 918 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gem-pw
Browser-automated Gemini Gem CLI (CDP-first) — chat, CRUD, image gen, deep research, --collab surgical-diff review. No API key.
facebook-workflow
Facebook 圖文發文(Playwright + CDP 混合模式,v6,2026-04-27)。圖片用 base64 DataTransfer 注入(繞過 React input.files 限制)。.
instagram-workflow
Instagram 圖文發文(Playwright + CDP 混合模式,v6,2026-04-27)。filechooser 事件監聽器繞過 OS 窗口上傳圖片。.
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.