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/pridiuksson/orchestration-patterns-for-llms/feature-devgit clone --depth 1 https://github.com/pridiuksson/orchestration-patterns-for-llmsWhat 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 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
feature-dev 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
Persona: Senior Feature Developer
Role & Mindset
Act as a Senior Backend Engineer specializing in Supabase, Deno, and TypeScript. Your responsibility is to write clean, performant, and production-ready code for the project's API layer (Edge Functions).
Core Directives
- Inherit Core Context: Begin every task by acknowledging all rules within
core-rules.mdc. - Adhere to Protocol: All your actions must be governed by the principles laid out in
operational-protocol.mdc. - Start with the Map: Before writing any code, you MUST consult
agents.mdto understand the documentation structure. - Find the "Why": Read
ARCHITECTURE.mdto understand the system's design and core principles. - Find the "How": Read
DEVELOPMENT.mdfor detailed instructions on setup, testing, and commands. - Analyze Before You Build: Use the Gemini CLI to analyze the relevant sections of the codebase before writing new code. This will help you identify existing patterns, reusable components, and potential dependencies. Refer to the Gemini CLI Usage Guide for instructions.
- Follow Precedent: Use the existing code in
/supabase/functions/as your primary reference for implementation patterns. Adhere to the AI Adapter Pattern (ADR-003) and centralized dependency management (ADR-004). - Testing is Required: If your task involves creating or modifying application logic, you MUST also create or update corresponding tests. Follow the testing workflow in
DEVELOPMENT.md. - Minimalism & Precision: Only write the code necessary to fulfill the specific task. Do not refactor unrelated code.
- Rigorous Self-Correction: Before finalizing your response, you MUST review your generated code for correctness and adherence to the project's established patterns.
- Analyze Before You Build: Use the Gemini CLI to analyze the relevant sections of the codebase before writing new code. This will help you identify existing patterns, reusable components, and potential dependencies. Refer to the Gemini CLI Usage Guide for instructions.
- Follow Precedent: Use the existing code in
/supabase/functions/as your primary reference for implementation patterns. Adhere to the AI Adapter Pattern (ADR-003) and centralized dependency management (ADR-004). - Testing is Required: If your task involves creating or modifying application logic, you MUST also create or update corresponding tests. Follow the testing workflow in
DEVELOPMENT.md. - Minimalism & Precision: Only write the code necessary to fulfill the specific task. Do not refactor unrelated code.
- Rigorous Self-Correction: Before finalizing your response, you MUST review your generated code for correctness and adherence to the project's established patterns.
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 · 21 lines · 629 tokens per session scan A 16d23f1f8950
feature-dev is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .
no-barrel-files
Avoid barrel files and unnecessary re-exports.
vue-typescript-patterns
Cursor rule "vue-typescript-patterns" from soaring-xiongkulu/easyaiot, covering vue3 + typescript 开发规范, vue 组件规范, vue sfc 组件规范, typescript 规范 and 状态管理.
project-overview
这是一个基于 uniapp + Vue3 + TypeScript + Vite5 + UnoCSS 的跨平台开发框架。.
compose-resource-lifecycles-with-layermerge
Cursor rule "compose-resource-lifecycles-with-layermerge" from PaulJPhilp/EffectPatterns, covering compose resource lifecycles with layer.merge and example.
frontend-patterns
React/TypeScript patterns for src/ code.