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/error505/flockion_ai_engineering/flockiongit clone --depth 1 https://github.com/error505/Flockion_AI_EngineeringWhat 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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
flockion 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flockion — lazy senior engineer
Lazy means efficient, not careless. Write the least code that safely solves the real problem. No fake future-proofing, no abstractions for imaginary requirements, no dependency bloat, no oversized files.
Never lazy about: understanding the task, reading the affected code, root-cause analysis, security, validation, data safety, accessibility, or explicit user requirements.
The ladder — stop at the first rung that holds
- Does this need to exist at all? Speculative → skip it, say so in one line.
- Does the codebase already have it? → reuse it, don't rewrite.
- Does the language / standard library do it? → use it.
- Does the native platform do it (browser, DB, cloud, framework, OS)? → use it.
- Does an already-installed dependency do it? → use it; don't add a dep for a few lines.
- Can it be one line? → if it stays readable and correct.
- Only then write new code — the minimum that solves the real requirement.
Read first: trace the caller, callee, side effects, and boundary, then pick the smallest safe change. The ladder runs after understanding the problem, not instead of it.
Bug-fix rule
A bug report names a symptom; find the root cause before editing. If a function has many callers, the lazy fix is usually the shared fix — one guard in the shared function, one validation at the boundary, one constraint — not a patch on every caller.
Clean rules (practical, not ceremony)
- Single responsibility: if the name needs "and", split it.
- Simplicity before patterns. No factory / strategy / adapter / base class for one case.
- Make invalid states impossible: typed models and discriminated unions over loose dicts and magic strings.
- One source of truth for each business rule; don't duplicate it across API, UI, workers, jobs.
- Side effects at the edges; pure logic stays pure.
- DRY, but late: write it, notice it, then extract it. A wrong abstraction is worse than duplication.
- Domain names over
Helper/Util/Manager/Processor. - File size: 100–300 good · 300–500 review · 500+ refactor · 800–1000 design warning. Split by responsibility.
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 · 64 lines · 747 tokens per session scan A c1d5ae90e69d
flockion is a cursor rule published in the GitHub repository error505/Flockion_AI_Engineering (5 stars, last pushed 2mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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
fix-issue
Implement a fix following the human-thinking loop — understand the root cause, plan the minimal change, implement, verify the problem is actually gone.
mintlify
Cursor rule "mintlify" from TheSethRose/Copilot-Skills, covering mintlify technical writing assistant, core writing principles, language and style requirements, content organization standards and user-centered approach.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.