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 instructions/h34tsink/websight/copilot-instructionsgit clone --depth 1 https://github.com/h34tsink/websightWrote 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/instructions/h34tsink/websight/copilot-instructions)<a href="https://agentmods.dev/instructions/h34tsink/websight/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/h34tsink/websight/copilot-instructions.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 | $0.00831 | $0.00831 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
websight copilot-instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebSight - Visual Analysis & Interaction Tools
This workspace contains WebSight, a visual analysis and page interaction tool for AI-assisted UI work.
Quick Reference
| Action | Purpose | When to Use |
|---|---|---|
look |
Analyze page structure, theme, CSS vars, interactive elements | First step - understand the page |
baseline |
Save current visual state | Before making any code changes |
diff |
Compare current vs baseline, get % pixel difference | After code changes to verify |
click |
Click buttons, links, toggles | Testing interactions |
type |
Enter text into inputs/textareas | Form testing |
select |
Choose dropdown options | Form testing |
hover |
Hover over elements | Test hover states |
scroll |
Scroll page (up/down/top/bottom) | Navigate page |
press |
Press keyboard keys (Enter, Escape, Tab) | Keyboard navigation |
WORKFLOW: Visual Changes
When user says "use websight" for ANY visual change:
1. look → Understand current state (CSS vars, sections, theme)
2. baseline → Save before state
3. [edit] → Make code changes
4. diff → Verify changes (check % difference)
5. [iterate if needed]
WORKFLOW: Interaction Testing
When user wants to test page interactions:
1. look → Get list of interactive elements with testIds
2. click/type/select/hover → Interact using testId or element text
3. look → Verify state changed
Targeting Elements
WebSight finds elements in this priority order:
- data-testid -
click("btn-save")finds[data-testid="btn-save"] - Accessible name -
click("Submit")finds button with text "Submit" - CSS selector -
click("#my-button")orclick(".submit-btn")
Pro tip: Use short testIds without prefixes. field-name not [data-testid="field-name"]
Available MCP Tools
websight_look / websight(action="look")
Returns: CSS variables, theme colors, sections, landmarks, interactive elements with testIds
websight_baseline / websight(action="baseline")
Saves: Screenshot + snapshot.json for comparison
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 · 94 lines · 831 tokens per session scan A 3d65c6d2dd98
websight copilot-instructions.md is an instructions file published in the GitHub repository h34tsink/websight (0 stars, last pushed 6mo ago), licensed MIT. It adds 831 tokens to every session, about $0.0042 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 instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.
shantycrawl-mcp AGENTS.md
AGENTS.md instructions for schlemperdev/shantycrawl-mcp, covering shantycrawl mcp -- dynamic firecrawl mcp server, purpose, ownership, local contracts and work guidance.