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 AllenS0104/skill-browser --skill site-profilegit clone --depth 1 https://github.com/AllenS0104/skill-browserWrote 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/allens0104/skill-browser/site-profile)<a href="https://agentmods.dev/skills/allens0104/skill-browser/site-profile"><img src="https://agentmods.dev/badge/skills/allens0104/skill-browser/site-profile/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/allens0104/skill-browser/site-profile"><img src="https://agentmods.dev/badge/skills/allens0104/skill-browser/site-profile.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 | $0.00035 | $0.00552 |
| Opus 5.5 | $0.00014 | $0.00221 |
| Sonnet 5.5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
site-profile 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site profile skill
This is the short public alias for:
external-site-profile-learning
Also available as simpler aliases:
profile站点配置
Use this skill when you want to:
- add a new external site profile
- debug why a site works heuristically but fails under Gemini
- classify whether a site should be generic, blocked, special, or config-driven
- validate a site in both heuristic and Gemini modes
Primary guidance
Follow the same workflow as the full skill:
- probe the site
- classify the UI pattern and failure mode
- add a data-only profile when justified
- validate heuristic and Gemini flows
- keep special/rate-limited sites out of the default regression matrix
- use grouped regression runs when debugging popup-heavy or heavy-page sites
Key rules
- Prefer URL or title verification for external sites.
- Prefer exact selectors over broad selectors.
- If a profile exists, normalize generated
typeandclicksteps back to the profile selectors. - Treat login walls, hidden inputs, duplicate controls, and anti-bot behavior as different problem types.
- Prefer grouped validation commands such as
validate:external:core,validate:external:popup, andvalidate:external:heavyfor targeted debugging.
Quick invocation template
You do not need to use only /site-profile.
Reliable invocation patterns include:
/site-profileuse the site-profile skill- a natural-language request that clearly asks to turn an already-proven flow into a stable reusable profile
Use prompts like:
Use /site-profile to turn this site into a stable external profile, then validate both heuristic and Gemini planning.
使用 /site-profile 把这个网站沉淀成稳定 profile，并分别验证 heuristic 和 Gemini 两条链路。
Please turn this already-working site flow into a stable reusable profile and validate both heuristic and Gemini modes.
Output contract
The skill output should always include:
- failure class or site class
- exact selectors chosen and why
- verification mode and expected signal
- validation commands run (or planned)
- final status: stable / blocked / special-case
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 · 83 lines · 35 tokens per session scan A cde5b4cc610d
site-profile is a skill published in the GitHub repository AllenS0104/skill-browser (5 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 552 once invoked, about $0.0001 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
moab-browser-automation
MOAB — build a dedicated browser-automation agent for a website the user already logs in to. Use when the user mentions MOAB, asks to automate a portal, dashboard, intranet site, or SaaS tool, wants an AI agent for a site behind SSO or single sign-on, or asks to add a new tool or feature to an existing MOAB agent.…
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
core
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across…
derive-client
Reverse-engineer a website's internal API by recording browser traffic into a HAR file, then generate a standalone client or CLI that calls the endpoints directly, with no browser needed after the first recording. Use when asked to "derive a client", "build a CLI for ", "reverse engineer this site's API", "record…