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/marlonjd/web-debug-mcp/web-debug-workflownpx skills add MarlonJD/web-debug-mcp --skill web-debug-workflowgit clone --depth 1 https://github.com/MarlonJD/web-debug-mcpWhat 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 | $0.00070 | $0.02134 |
| Opus 5 | $0.00035 | $0.01067 |
| Sonnet 5 | $0.00014 | $0.00427 |
| Haiku 4.5 | $0.00007 | $0.00213 |
Grade A, and why
web-debug-workflow 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 74 lines · 70 tokens per session scan A b48b4f35ab4c
web-debug-workflow is a skill published in the GitHub repository MarlonJD/web-debug-mcp (6 stars, last pushed 2d ago), with no licence file. It adds 70 tokens to every session and 2,134 once invoked, about $0.0003 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
aim-browser
Headed Chromium CDP CLI: tabs, navigate, click/type, extract, screenshots, optional captcha hold helper. Use for general page exploration when a one-verb skill is not enough. Not Puppeteer/Playwright.
aim-google-ai
Google Search AI Mode (udm=50) via headed Chromium. Returns answer text and sources as markdown + JSON. Use for AI Mode answers, not classic blue links.
aim-form-fill
Fill form fields on an allowlisted host. Requires --allow-host and --fields. Never submits unless --submit. Redacts password-like values in output.
aim-login-hold
Open a URL and wait for Operator human login or CAPTCHA. Continues when --ready-file is created or URL matches --until-url-includes. Never captures passwords. Window visible by default for this skill.
aim-google-ai-chat
Multi-turn Google AI Mode via headed Chromium. Initial query uses udm=50; --follow-up / --turns for more turns. Prefer aim-google-ai for single-shot.
aim-page-fetch
Open a URL in headed Chromium and extract title, meta, main text, and links. Markdown + JSON. Use when page content must be live, not invented.