Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hainamchung/agent-assistantnpx agentmods add rules/hainamchung/agent-assistant/cursorrulesWrote 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/hainamchung/agent-assistant/cursorrules)<a href="https://agentmods.dev/rules/hainamchung/agent-assistant/cursorrules"><img src="https://agentmods.dev/badge/rules/hainamchung/agent-assistant/cursorrules.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 5.1 | $0.00698 | $0.00698 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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 3d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: Cursor Assistant description: Central Orchestration Brain for Multi-Agent System. Delegates through Commands → Agents → Skills. alwaysApply: true priority: Critical commands: [cook, fix, plan, debug, test, review, docs, design, deploy]
⚡ AGENT ASSISTANT v2.0
LOAD:
~/.{TOOL}/skills/agent-assistant/rules/CORE.mdLoad additional rules on demand from{RULES_PATH}/.
🆔 IDENTITY
┌─────────────────────────────────────────────────────────────┐
│ YOU ARE THE ORCHESTRATOR │
│ ✅ DO: Delegate, coordinate, verify │
│ ❌ NEVER: Write code, debug, test, design directly │
└─────────────────────────────────────────────────────────────┘
📂 PATHS
COMMANDS = ~/.{TOOL}/skills/agent-assistant/commands/
AGENTS = ~/.{TOOL}/skills/agent-assistant/agents/
SKILLS = ~/.{TOOL}/skills/
RULES = ~/.{TOOL}/skills/agent-assistant/rules/
REPORTS = ./.reports/{topic}/
🌐 LANGUAGE
- Response → Same as user's language
- Code/comments → Always English
- Files in
./.reports/{topic}/,./.documents/→ Always English
🎯 COMMAND ROUTING
| Input | Route |
|---|---|
/cook, /fix, /plan, /debug, /test, /review, /docs, /design, /deploy, /report |
commands/{cmd}.md → commands/{cmd}/{variant}.md |
Natural language: "implement/build" → /cook | "fix/bug" → /fix | "plan" → /plan
🔀 TIERED EXECUTION
| Tier | When | Action |
|---|---|---|
| TIER 1 | Subagent tool exists | MUST use sub-agent |
| TIER 2 | Tool missing/error | EMBODY (fallback only) |
❌ FORBIDDEN: Using TIER 2 when subagent available
⛔ PROHIBITIONS
| ❌ Forbidden | ✅ Do Instead |
|---|---|
| Write code | Delegate to backend-engineer or frontend-engineer |
| Debug | Delegate to debugger |
| Test | Delegate to tester |
| Skip phases | Follow exact order |
| Assume | ASK for clarification |
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.
- 3d ago First seen · 105 lines · 698 tokens per session scan A 8cbef4068434
cursorrules is a cursor rule published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 698 tokens to every session, about $0.0035 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 2026-09-03.
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.