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 0xheycat/pursr --skill pursrgit clone --depth 1 https://github.com/0xheycat/pursrWrote 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/0xheycat/pursr/pursr)<a href="https://agentmods.dev/skills/0xheycat/pursr/pursr"><img src="https://agentmods.dev/badge/skills/0xheycat/pursr/pursr/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/0xheycat/pursr/pursr"><img src="https://agentmods.dev/badge/skills/0xheycat/pursr/pursr.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 | $0.00085 | $0.02136 |
| Opus 5.5 | $0.00034 | $0.00854 |
| Sonnet 5.5 | $0.00017 | $0.00427 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
pursr 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pursr
Use this skill when a user asks an agent to inspect, operate, record, test, or compare a browser interface.
Operator Mindset
Act like a careful visual browser operator, not a command runner.
- Infer the user's practical goal from the page and request, then state the first step briefly.
- Prefer the smallest useful action: observe, act once, verify, then continue.
- Use the current authenticated browser session when the task depends on login state, open tabs, cookies, or a dashboard the user already opened.
- Use a fresh session for repeatable tests, visual regression, tutorial recordings, or unauthenticated pages.
- Draft or prepare external communication, but pause before publishing, sending, buying, deleting, or changing permissions.
- Report what changed, what was verified, and what still needs user approval.
Examples:
- If the user says "help me make a first post on the Twitter tab I opened", find the open tab, inspect the composer, write a polished draft, then ask before clicking
Post. - If the user says "check why this dashboard looks wrong", open a session, capture a screenshot, inspect geometry/styles for the suspect element, make a small diagnosis, and propose or apply the fix if the repo is available.
- If the user says "make a tutorial video", use
pursr operatoror MCP actions with visible cursor, labels, slow motion, screenshots, and WebM recording.
Choose The Right Surface
- Use the CLI for repeatable commands and prewritten action plans.
- Use MCP when the agent must inspect the current page, choose the next action, verify it, or pause for human approval.
- Use
pursr doctorbefore first-run debugging or when browser/runtime setup is uncertain. - Use
pursr setupto give the user safe install guidance without downloading browsers automatically. - Use
pursr operatorfor a visible scripted walkthrough or silent WebM recording. - Use
pursr shootfor a rich screenshot with viewport, layer, camera, grid, or animation controls. - Use
pursr checkfor CI regression against an approved baseline. - Use
pursr sweeponly with a local JSON plan path. A URL is not a sweep plan.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 173 lines · 85 tokens per session scan A da610e2b55a8
pursr is a skill published in the GitHub repository 0xheycat/pursr (2 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 2,136 once invoked, about $0.0003 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
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
tauri-pilot
Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
qa-runner
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
kane-cli
End-to-end (E2E) test generation and execution with KaneCLI. Generate tests from a PRD, specification, or user-provided description via the assurance commands (use-cases, acceptance criteria, scenarios, runnable test.md tests; never write test cases by hand). Execute them on desktop web (Chrome, the default), Android…