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 skills add Stijnman/grok-custom-skills --skill humanization-stealth-browsinggit clone --depth 1 https://github.com/Stijnman/grok-custom-skillsWrote 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/stijnman/grok-custom-skills/humanization-stealth-browsing)<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/humanization-stealth-browsing"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/humanization-stealth-browsing/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/stijnman/grok-custom-skills/humanization-stealth-browsing"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/humanization-stealth-browsing.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 | $0.00043 | $0.00477 |
| Opus 5.5 | $0.00017 | $0.00191 |
| Sonnet 5.5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
humanization-stealth-browsing 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 1mo 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
Responsible Web Browsing
When to Use
Use this skill when collecting information from public websites requires careful pacing, stable navigation, or respect for fragile endpoints. It supports responsible research, not bypassing protections.
Do not use this skill to evade bot detection, bypass access controls, defeat CAPTCHAs, circumvent paywalls, or access content that the user is not authorized to view.
Workflow
- Confirm that the target is public and that the requested collection is legitimate.
- Prefer official APIs, published feeds, or a site’s documented export options.
- Review and respect applicable terms,
robots.txt, rate limits, and access restrictions. - Make requests incrementally, cache results where appropriate, and avoid unnecessary retries.
- If a login wall, CAPTCHA, paywall, or block appears, stop and explain the limitation to the user.
Operating Principles
| Principle | Practice |
|---|---|
| Minimize load | Use measured request rates and avoid broad, repetitive crawling. |
| Preserve provenance | Record source URLs and retrieval dates for material findings. |
| Respect controls | Do not rotate identities, automate CAPTCHA solving, or bypass authentication. |
| Fail safely | Stop rather than escalating when a site signals restricted access. |
Error Handling
| Situation | Response |
|---|---|
| Rate limit or temporary block | Pause activity and offer a slower or official-data-source alternative. |
| CAPTCHA or login wall | Stop the automated flow; ask the user to provide authorized access if appropriate. |
robots.txt or terms restrict collection |
Do not scrape the restricted path; propose permitted alternatives. |
| Source data is incomplete | State the limitation and avoid filling gaps with assumptions. |
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.
- 1mo ago First seen · 47 lines · 43 tokens per session scan A 7d1f10135684
humanization-stealth-browsing is a skill published in the GitHub repository Stijnman/grok-custom-skills (13 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 477 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 2026-08-31.
Other skills, from other repositories
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
browser-reset
Reconfigure the browser-control wiring. Rotate the Playwright MCP Bridge token, switch the target browser, or fully tear down the AIWG registration and provider injection. Walks the user through extension UI regeneration where needed; respects human-authorization gates for destructive operations.
browser-setup
Interactive wizard that wires up @playwright/mcp end-to-end — detects the user's browsers, walks through Playwright MCP Bridge extension install, captures the per-install token, registers the MCP server in the AIWG registry with --extension and the env block, injects into the active provider's config, and verifies the…
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
steward
Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.