route

A command that examines a problem description and recommends matching problem-solving agents. It compares the problem with an index of agent roles and explains why each match fits.

In plain words
What is it for?
Use it to find one to three candidate agents, understand their fit, and plan an order for combining them.
Why use it?
It helps choose suitable agents when you do not know which analysis method to use.

Command for Claude Code

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 commands/cdeust/ai-architect-mcp-codebase/route
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00301
Opus 5 $0.00000 $0.00151
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash 3a6b93d2ca3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

route 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.

.claude/commands/genius/route.md · 27 lines

What it actually says

Route Problem to Genius Agents

Analyze a problem description, find matching genius agent shapes, and recommend agents.

Instructions

  1. Take the problem description from $ARGUMENTS.

  2. Run tools/genius-invoker.sh route "$ARGUMENTS" to search INDEX.md for matching shapes.

  3. Read agents/genius/INDEX.md directly. For each keyword in the problem description, scan the Shape tables for matching triggers. Look for:

    • Exact shape name matches
    • Trigger condition matches (the "Trigger" column describes when the shape activates)
    • Semantic matches where the problem structure fits a shape even without keyword overlap
  4. Rank recommendations by match quality. For each recommended agent (1-3 max), output:

    • Agent name and link to its file
    • Matching shape(s) with the trigger text from INDEX.md
    • Why it matches — connect the problem's structure to the shape's trigger
    • Key move — what the agent will do first
  5. If multiple agents match, suggest a composition sequence: which agent to run first and why, what its output feeds into the next agent, and the expected combined insight. Reference tools/genius-invoker.sh compose for execution.

  6. If no shapes match, say so clearly. Suggest the user try a standard team agent instead or rephrase the problem to expose its structural shape.

$ARGUMENTS

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 · 27 lines · 0 tokens per session scan A 3a6b93d2ca3b

Subscribe to this mod's changes

route is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 301 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 2026-08-31.