map-agents

map-agents is a command for Claude Code from Owl-Listener/ai-design-skills. It costs 11 tokens per session (470 once invoked), scanned A, original, MIT.

A command for mapping the structure of a system made of multiple AI agents. It shows each agent's responsibilities, limits, tools, decision power, and communication links.

In plain words
What is it for?
Inventorying agents, drawing communication paths, defining role boundaries, mapping autonomy, and locating where human approval is needed.
Why use it?
It exposes missing responsibilities, overlapping roles, communication bottlenecks, and unclear approval points.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the design-agent-orchestration plugin — 7 skills, 3 commands shipped together

Good fit Inventorying agents, drawing communication paths, defining role boundaries, mapping autonomy, and locating where human approval is needed.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/ai-design-skills/map-agents
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.

Clone the repo
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skills

Made for: Claude Code.

Or install design-agent-orchestration, the plugin that ships this one along with the rest of its 7 skills, 3 commands.

Wrote 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.

agentmods badge for map-agents

README.md
[![agentmods](https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/map-agents/github.svg)](https://agentmods.dev/commands/owl-listener/ai-design-skills/map-agents)
Your own site
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/map-agents"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/map-agents/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for map-agents

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/map-agents"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/map-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.00470
Opus 5 $0.00005 $0.00235
Sonnet 5 $0.00002 $0.00094
Haiku 4.5 $0.00001 $0.00047

Measured 9d ago against content hash 5301532af472, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

map-agents 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 9d 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.

claude-plugin/design-agent-orchestration/commands/map-agents.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are mapping the agent architecture of a multi-agent system. Use only skills from the design-agent-orchestration plugin. Follow this process:

Step 1: Inventory the Agents

List every agent in the system (or planned for the system):

  • What is each agent called?
  • What is its stated purpose?
  • What tools and data does it have access to?

Step 2: Define Roles Formally

Using agent-role-design:

  • For each agent, create a complete role card
  • Identify role patterns (specialist, router, orchestrator, validator, fallback)
  • Check for gaps: are there tasks no agent covers?
  • Check for overlaps: do multiple agents claim the same territory?

Step 3: Map Communication Patterns

Using handoff-protocols:

  • Draw the communication graph: which agents talk to which?
  • For each connection, define the handoff protocol
  • Identify one-way vs. bidirectional communication
  • Find bottlenecks: agents that everything flows through

Step 4: Map Authority and Autonomy

Using agent-role-design and human-in-the-loop:

  • For each agent, map autonomy level: full, supervised, advisory, passive
  • Identify which agents can make decisions independently
  • Map where human approval is required
  • Check that authority matches stakes

Step 5: Analyse Dependencies

Using state-management and task-decomposition:

  • Map data dependencies between agents
  • Identify critical paths where one agent blocks others
  • Find circular dependencies
  • Assess the impact of each agent failing on the rest of the system

Step 6: Identify Risks

Using failure-recovery:

  • For each agent, what happens if it fails?
  • For each communication link, what happens if it breaks?
  • Identify single points of failure
  • Assess cascading failure risk

Output

Deliver a complete agent map:

  1. Agent inventory with role cards
  2. Communication graph with handoff protocols
  3. Authority and autonomy matrix
  4. Dependency analysis with critical paths
  5. Risk assessment with single points of failure
  6. Recommendations for architecture improvements

Read the full file on GitHub · 50 lines

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. 9d ago First seen · 50 lines · 11 tokens per session scan A 5301532af472

Subscribe to this mod's changes

map-agents is a command published in the GitHub repository Owl-Listener/ai-design-skills (171 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 470 once invoked, about $0.0001 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 2026-08-30.