cursorrules

A set of project instructions for Vigilis, a tool that creates and maintains Playwright browser tests. Playwright tests check whether a website or web app works correctly in a real browser.

In plain words
What is it for?
Use it to orient an agent in the Vigilis codebase, follow its TypeScript and pnpm conventions, and run linting, type checks, tests, and builds before reporting completion.
Why use it?
It gives coding agents the project context, design decisions, current work, and required checks before they change code. This helps prevent false claims that work is finished.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/piyushpathakqa/vigilis/cursorrules
Clone the repo
git clone --depth 1 https://github.com/piyushpathakqa/Vigilis

Made for: Cursor.

Per session 204 This file is loaded in full into every session.
When invoked 204 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00204 $0.00204
Opus 5 $0.00102 $0.00102
Sonnet 5 $0.00041 $0.00041
Haiku 4.5 $0.00020 $0.00020

Measured 2d ago against content hash 9f33ebb4cbac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 15 lines

What it actually says

Vigilis — Cursor context pointer

This is Vigilis, an agentic QA framework (Claude authors/generates/triages/self-heals Playwright tests; ships as an MCP server + CLI; gated in GitHub Actions).

Before doing anything, read these in order:

  1. AGENTS.md — fast orientation, conventions, commands
  2. docs/STATUS.md — current state, what's done, what's next, how to resume
  3. docs/DESIGN.md — architecture and the rationale behind every decision
  4. docs/ROADMAP.md — milestones M0–M4 mapped to Linear tickets TRE-22..45

Key conventions: TypeScript + ESM, pnpm workspaces, tsup build, Vitest, ESLint flat config. Verify with: pnpm lint && pnpm typecheck && pnpm test && pnpm build. Never claim done without running them. Current next task: TRE-30 (the sample-shop Next.js app).

Changes

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.

  1. 2d ago First seen · 15 lines · 204 tokens per session scan A 9f33ebb4cbac

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository piyushpathakqa/Vigilis (5 stars, last pushed 13d ago), licensed MIT. It adds 204 tokens to every session, about $0.0010 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.