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.
git clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/commands/latestaiagents/agent-skills/design-agent)<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/design-agent"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/design-agent.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 | $0.00009 | $0.01146 |
| Opus 5 | $0.00005 | $0.00573 |
| Sonnet 5 | $0.00002 | $0.00229 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
design-agent 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 7d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-agent
Design a multi-agent system architecture with proven patterns.
Tell Me About Your System
To recommend the right architecture, I need to know:
-
What problem are you solving?
- Customer support automation
- Code generation pipeline
- Research and analysis
- Content creation workflow
- Data processing pipeline
-
How many agents do you need?
- 2-3 agents (simple delegation)
- 4-7 agents (specialized team)
- 8+ agents (complex swarm)
-
How should they coordinate?
- One agent controls others (Supervisor)
- Agents talk to each other (Mesh)
- Strict pipeline (Sequential)
- Dynamic based on task (Adaptive)
Architecture Patterns
Pattern 1: Supervisor (Hub-and-Spoke)
Best for: Clear hierarchy, centralized control, audit requirements
┌─────────────┐
│ Supervisor │ ← Makes decisions, delegates
└──────┬──────┘
┌───────┼───────┐
▼ ▼ ▼
┌───────┐┌───────┐┌───────┐
│Agent A││Agent B││Agent C│ ← Specialized workers
└───────┘└───────┘└───────┘
Use when:
- You need clear accountability
- Tasks can be cleanly separated
- You want predictable behavior
Pattern 2: Mesh (Peer-to-Peer)
Best for: Complex tasks, emergent behavior, resilience
┌───────┐ ┌───────┐
│Agent A│◄───►│Agent B│
└───┬───┘ └───┬───┘
│ ╲ ╱ │
│ ╲ ╱ │
▼ ╳ ▼
┌───────┐ ╱ ╲┌───────┐
│Agent C│◄───►│Agent D│
└───────┘ └───────┘
Use when:
- Tasks require collaboration
- Agents have overlapping knowledge
- System needs fault tolerance
Pattern 3: Pipeline (Sequential)
Best for: Ordered workflows, data transformation, quality gates
Input → [Agent A] → [Agent B] → [Agent C] → Output
│ │ │
▼ ▼ ▼
Validate Process Format
Use when:
- Tasks have natural order
- Each stage transforms data
- You need checkpoints
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.
- 7d ago First seen · 167 lines · 9 tokens per session scan A 488dab5543b2
design-agent is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 1,146 once invoked, about $0.0000 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 commands, from other repositories
fdk-react-create
Create a new Platform 3.0 React Meta app (default UI stack). Uses fdk create react-starter-template or react-meta skeletons with DEW components, metaConfig in manifest.json, and React Router.
fdk-refactor
Reduce function complexity in a Freshworks app to meet cyclomatic complexity ≤ 7 per function. Extracts helper functions, simplifies conditionals, and preserves behavior while improving code quality.
fw-setup-uninstall
Uninstall FDK completely — keeps Node.js and nvm (/fw-setup uninstall).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.