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 smileynet/teach-me --skill browse-and-verifygit clone --depth 1 https://github.com/smileynet/teach-meWrote 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/smileynet/teach-me/browse-and-verify)<a href="https://agentmods.dev/skills/smileynet/teach-me/browse-and-verify"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/browse-and-verify/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/smileynet/teach-me/browse-and-verify"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/browse-and-verify.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 | $0.00052 | $0.00880 |
| Opus 5 | $0.00026 | $0.00440 |
| Sonnet 5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
browse-and-verify 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browse and Verify
Dispatch to the browser specialist agent (.kiro/agents/browser.json) for URL validation, section extraction, and heading discovery. The browser agent has the Playwright MCP configured — the default agent does NOT load Playwright (40+ tools would degrade tool selection).
Setup
The browser agent is at .kiro/agents/browser.json with @playwright/mcp configured headless. Dispatch to it for any browsing task rather than loading Playwright in the main context.
If the browser agent is unavailable, fall back to the web_fetch tool (built-in, no MCP needed).
When to use
- Before adding a quiz source link: navigate to the URL, verify the page loads and the content exists
- When finding the right section to link: browse the page and look for heading IDs/anchors
- When writing explanations: read the relevant section to ground your explanation in the source
- When a learner questions a source: re-read the section to confirm accuracy
Workflow: Validate and find the right section
- Navigate to the page URL
- Check the snapshot — does the page load? Is the content relevant?
- Find headings — look for section IDs in the accessibility snapshot to construct
#anchorlinks - Read the section — confirm the content actually answers/addresses the quiz question
- Write the source entry with the specific URL#anchor, label, and section description
Quality rules for quiz source links
- Always browse before committing — dead links and irrelevant pages erode trust
- Link to the most specific section — use
#anchorIDs from headings - Read the section to confirm it actually helps answer the question
- Write the
sectionfield based on what you read, not assumptions - If no good anchor exists, link to the page and describe which paragraph is relevant
- Never link to generic overviews — the linked page must significantly help answer the specific question
- Multiple targeted links > one vague link — e.g., both the spec section AND the AWS implementation docs
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.
- 11d ago First seen · 76 lines · 52 tokens per session scan A 3b48d318bb4f
browse-and-verify is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 880 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
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
textbook-distillation
Turn a textbook or long-form source into a self-paced learning track: chapter map, lesson plan, then self-contained HTML lecture notes (styled as the human specifies) with worked examples, exercises, and checkpoint questions. Read this for "lecture notes" / "study notes" / "course" / "syllabus" requests from a…
learning-notes-automation
A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.
antivibe
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.