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/sijeeshmiziha/visionagent/multi-agent-systemsgit clone --depth 1 https://github.com/sijeeshmiziha/visionagentWrote 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/sijeeshmiziha/visionagent/multi-agent-systems)<a href="https://agentmods.dev/rules/sijeeshmiziha/visionagent/multi-agent-systems"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/multi-agent-systems.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 | $0.00834 | $0.00834 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
multi-agent-systems 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Systems
When to Use Multi-Agent
- Best for open-ended, path-dependent tasks (e.g. research) where steps can’t be hardcoded; single linear pipelines are insufficient.
- Subagents provide compression (parallel context windows, then condense for the lead) and separation of concerns (distinct tools, prompts, trajectories).
- Strong fit: breadth-first, parallelizable work; information exceeding one context window; many tools. Token usage drives much of performance; multi-agent scales token capacity.
- Poor fit: tasks requiring shared context or heavy inter-agent dependencies; multi-agent uses ~15× tokens vs chat—reserve for high-value tasks.
Orchestrator-Worker Pattern
- Lead agent: analyzes query, plans strategy, spawns subagents (in parallel), synthesizes results, decides if more work is needed.
- Subagents: clear objective, output format, guidance on tools/sources, task boundaries. Vague delegation causes duplicated work, gaps, or misinterpretation.
- Scale effort to query: e.g. simple (1 agent, 3–10 tool calls), comparison (2–4 subagents, 10–15 each), complex (10+ subagents with divided responsibilities). Embed scaling rules in prompts to avoid over- or under-investment.
Parallel Execution and Thinking
- Parallelize: lead spawns 3–5 subagents in parallel; subagents use 3+ tools in parallel where possible—large latency gains.
- Guide thinking: use extended thinking so the lead plans (complexity, subagent count, roles); subagents plan then evaluate tool results and refine next steps. Heuristics over rigid rules; add guardrails to prevent spiraling.
Prompting and Tools
- Think like your agents: simulate with exact prompts and tools (e.g. in Console) to see failure modes.
- Tool design: match tools to user intent; give heuristics (e.g. examine all tools, prefer specialized). Consider agents that test tools and rewrite descriptions to improve ergonomics.
- Search strategy: start broad, then narrow; avoid overly long, specific queries that return too little.
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 · 47 lines · 834 tokens per session scan A f85f2f41a0b6
multi-agent-systems is a cursor rule published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 834 tokens to every session, about $0.0042 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
Task queue orchestrator for AI agents. TypeScript + Hono + BullMQ + Redis.
arm_index
This file defines the installation priorities for rulesets managed by ARM.
grug-brained-dev_avoid-abstractions
Don't create abstractions until you have multiple concrete examples.
grug-brained-dev_complexity-enemy
Avoid unnecessary complexity in all forms.
grug-brained-dev_debuggable-code
Write code that is easy to debug and understand.
grug-brained-dev_simple-tools
Choose tools and libraries that are simple and well-understood.