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 rules/mrkanitkar/playwright-praman/pramangit clone --depth 1 https://github.com/mrkanitkar/playwright-pramanWrote 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/rules/mrkanitkar/playwright-praman/praman)<a href="https://agentmods.dev/rules/mrkanitkar/playwright-praman/praman"><img src="https://agentmods.dev/badge/rules/mrkanitkar/playwright-praman/praman.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 | $0.00805 | $0.00805 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
praman 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Praman v1.0 Rules
Architecture
- 5-layer: Core Infrastructure → Bridge Adapters → Typed Proxy → Fixtures → AI
- Single npm package
playwright-pramanwith sub-path exports - Lower layers NEVER import from higher layers
Code Rules
- TypeScript strict mode — no
any, noas unknown as T - ESM only in source (
import, neverrequire) - All public APIs: TSDoc with
@exampletag - Module size ≤ 300 LOC
- Use pino logger — NEVER
console.log - All errors extend
PramanErrorwithcode,attempted,retryable,suggestions[] - All relative imports include
.jsextension - Node builtins use
node:prefix (node:path,node:fs) - Config is
Readonly<PramanConfig>— never mutate - Path aliases:
#core/*,#bridge/*,#proxy/*,#fixtures/*
Cross-Platform
- Always use
node:pathmethods — never hardcoded/or\ - Always use
node:fs/promisesfor async file operations - No bash-only npm scripts — use Node.js built-ins
- Dual ESM+CJS build:
npm run check:exportsvalidates export map
Naming
- Files: kebab-case (
bridge-error.ts) - Types: PascalCase, no
Iprefix (BridgeAdapter) - Functions: camelCase (
findControl) - Constants: UPPER_CASE (
MAX_RETRY_COUNT) - Error codes:
ERR_SCOPE_DESCRIPTION - Booleans:
is/has/can/shouldprefix
Import Order
- Node built-ins (
node:path) - External packages (
zod,pino) - Internal (
#core/,#bridge/,#proxy/) - Parent (
../) - Sibling (
./)
Testing
- Unit: Vitest, hermetic (no network),
*.test.ts - Integration: Playwright,
*.spec.ts, usetest.step() - NEVER use
page.waitForTimeout()— usewaitForUI5Stable() - Coverage ≥ 90% statements, ≥ 85% branches
Error Pattern
throw new ControlError({
code: 'ERR_CONTROL_NOT_FOUND',
message: `Control not found: ${selector}`,
attempted: `Find control: ${JSON.stringify(selector)}`,
retryable: true,
suggestions: ['Verify control ID', 'Check page loaded'],
});
7 Mandatory Rules (SAP Test Generation)
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.
- 4d ago First seen · 89 lines · 805 tokens per session scan A 8c43d594d4f2
praman is a cursor rule published in the GitHub repository mrkanitkar/playwright-praman (11 stars, last pushed today), licensed Apache-2.0. It adds 805 tokens to every session, about $0.0040 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 2026-08-30.
Other cursor rules, from other repositories
testing
Comprehensive Testing Best Practices for Svelte 5 + vitest-browser-svelte.
cursorrules
Comprehensive Testing Best Practices for Svelte 5 + vitest-browser-svelte.
potion-yjs-dev-browser-test
Use when a Slate Yjs collaboration behavior is suspicious and Potion should be used as a live reference implementation through dev-browser, especially for offline/reconnect, selection, or history scenarios.
slate-ar-gate
Slate v2 Autoresearch gate loop. Repeats and logs existing test/typecheck/browser/editor-behavior gates, including full navigation/typing suites, without owning missing-test design or correctness fixes.
agent-browser-issue
Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.
cursor-rules
Playwright E2E testing patterns, conventions, and best practices.