multi-agent-coordination

A set of rules for dividing work between multiple software agents and keeping their communication and responsibilities clear.

In plain words
What is it for?
It helps organise multi-agent development by separating roles, documenting requirements, tracking work, and recording dependencies.
Why use it?
It catches unstructured TODO and FIXME comments and encourages explicit tasks, ownership, progress, and acceptance criteria.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/ivangrynenko/cursorrules/multi-agent-coordination
Clone the repo
git clone --depth 1 https://github.com/ivangrynenko/cursorrules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 320 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00320
Opus 5 $0.00000 $0.00160
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash ff0144b37a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-agent-coordination 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/multi-agent-coordination.mdc · 45 lines

What it actually says

Multi-Agent Coordination Standards

Ensures consistent coordination between different AI agents and roles.

actions:

  • type: enforce conditions:

    • pattern: "// TODO:|#\s*TODO:" message: "Convert TODO comments into structured task breakdowns for multi-agent coordination"

    • pattern: "function\s+[a-zA-Z]+Agent\s*\([^)]*\)" message: "Implement proper agent role separation and communication"

    • pattern: "// FIXME:|#\s*FIXME:" message: "Convert FIXME into specific tasks with acceptance criteria"

  • type: suggest message: | Multi-Agent Coordination Best Practices:

    • Separate Planner and Executor roles
    • Document task breakdowns and success criteria
    • Track progress in structured format
    • Use proper inter-agent communication
    • Maintain clear role boundaries
    • Focus on immediate, actionable solutions
    • Provide context for complex tasks
    • Use natural language for requirements
    • Break down complex workflows
    • Document dependencies between tasks

metadata: priority: high version: 1.0

Changes

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.

  1. 2d ago First seen · 45 lines · 320 tokens per session scan A ff0144b37a17

Subscribe to this mod's changes

multi-agent-coordination is a cursor rule published in the GitHub repository ivangrynenko/cursorrules (87 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 320 tokens. 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 2026-08-30.