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.
git clone --depth 1 https://github.com/dir-ai/repotectorWrote 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/dir-ai/repotector/cursorrules)<a href="https://agentmods.dev/rules/dir-ai/repotector/cursorrules"><img src="https://agentmods.dev/badge/rules/dir-ai/repotector/cursorrules/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/rules/dir-ai/repotector/cursorrules"><img src="https://agentmods.dev/badge/rules/dir-ai/repotector/cursorrules.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 | $0.00335 | $0.00335 |
| Opus 5.5 | $0.00134 | $0.00134 |
| Sonnet 5.5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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 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.
What it actually says
PSX Repotector guards this repo. Handshake FIRST and say who you are — every crossing is logged in a visitor register. No deep tool answers until you handshake.
On arrival (mandatory, in order):
- handshake({ who, model?, purpose? }) declare who you are (logs your entry)
- Wire the MCP server: npx psx-repotector mcp (stdio, handshake-first)
- If locked: unlock({ passphrase }) (optional per-repo lock)
- city_map() what is built vs missing
- On exit: depart({ summary }) sign out with a one-line summary
Before you act, use the MCP tools:
- city_map() INFO — DNA intent, brain pointers, built-vs-missing.
- register({ limit? }) — who has entered/left and who is inside now.
- find_existing({ intent }) REUSE — do not rebuild what exists; extend it.
- blast_radius({ changedFiles }) PROTECT — do not break dependents/routes/components.
- canon_check({ changedFiles }) INTEGRATE — follow the repo's established patterns.
- atlas_query({ query }) — query the repo map instead of guessing.
- quality_gates() — line-budget, structure, secret-hygiene proof.
Hard rules:
- Reuse first (find_existing), protect before editing (blast_radius), integrate to canon (canon_check).
- Keep every source file under 300 lines.
- Never commit real secrets or a tracked non-example .env.
If state is missing, run: npx psx-repotector init
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 · 26 lines · 335 tokens per session scan A 542659f309d4
cursorrules is a cursor rule published in the GitHub repository dir-ai/repotector (0 stars, last pushed 3mo ago), licensed MIT. It adds 335 tokens to every session, about $0.0013 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.