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/aiagentwithdhruv/ai-dev-stack/45-environment-configgit clone --depth 1 https://github.com/aiagentwithdhruv/ai-dev-stackWhat 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 | $0.00302 | $0.00302 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
45-environment-config 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.
What it actually says
Configuration rules:
- All environment-specific values must come from environment variables or config files.
- Use a single config module/service that validates all required env vars at startup.
- Fail fast on missing or invalid configuration — do not silently use defaults for critical values.
- Maintain .env.example with every required variable documented (no real values).
Environment parity:
- dev, staging, and production must use the same config structure.
- Environment-specific behavior must be controlled by explicit flags, not implicit detection.
- Database URLs, API keys, model endpoints, and feature flags must all be configurable per environment.
Secrets management:
- Never commit .env, credentials.json, token.json, or any file with real secrets.
- Use .gitignore to block secret files.
- In production, prefer secret managers (AWS Secrets Manager, Vercel env vars, VPS env files) over baked-in values.
- Rotate secrets on a schedule or after any exposure.
Validation expectations:
- Validate config at application startup, not at first use.
- Type-check config values (ports as int, URLs as valid URLs, booleans as bool).
- Log which config keys are loaded (never log values) for debugging.
Do not:
- Hardcode API keys, tokens, passwords, or URLs anywhere in source code.
- Use different config loading patterns across services in the same project.
- Commit .env files or any file listed in .gitignore.
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 · 32 lines · 302 tokens per session scan A 16ba9e93c9af
45-environment-config is a cursor rule published in the GitHub repository aiagentwithdhruv/ai-dev-stack (10 stars, last pushed 2mo ago), licensed MIT. It adds 302 tokens to every session, about $0.0015 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 cursor rules, from other repositories
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
cursorrules
Code exhibits taste — Torvalds' term for finding the formulation where special cases disappear. Seek representations where edge cases become impossible, the type system proves correctness, and the API guides users into the pit of success.
java
Modern Java: records, sealed classes, streams, virtual threads.
javascript
Modern JavaScript: ES2023+, async patterns, common traps.
accessibility
Accessibility: semantic HTML, ARIA, keyboard navigation, testing.
cross-tool-config
Cross-tool AI config: what transfers between Cursor, Claude Code, Copilot, Windsurf, Gemini, and Codex.