A navigable directory of specialized agents, organized by categories, problem-solving approaches, and pairings.

Use it to browse categories, list agents, search by keyword, inspect a category, or see which agents pair with a given one.

It helps you find the right agent or understand how agents relate without searching through their files manually.

index — Command by cdeust

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/index

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 462 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00462
Opus 5	$0.00000	$0.00231
Sonnet 5	$0.00000	$0.00092
Haiku 4.5	$0.00000	$0.00046

Measured 2d ago against content hash 99557b966982, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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/index.md · 33 lines

What it actually says

Genius Agent Index

Display the genius agent index in a navigable format. Filter by category, show pairings, or browse the full shape-to-agent lookup.

Instructions

Parse $ARGUMENTS for optional filters:
- No arguments: show all categories with agent counts
- index <category> — show shapes for a specific category (fuzzy match on category name)
- index --agents — list all agents with their descriptions
- index --pairs <agent> — show what pairs well with a given agent
- index --search <term> — search shapes, triggers, and agents by keyword
Category overview (no args): Read agents/genius/INDEX.md. Extract all ### category headers. For each category, count the shapes (table rows). Display as a numbered list:
```
1. Measurement, Signal, and Isolation (5 shapes) — curie
2. Estimation and Bounding (5 shapes) — fermi
...
```
Tell the user they can drill into any category by number or name.
Category detail: Find the matching ### section in INDEX.md (case-insensitive partial match). Display the full shape table for that category. Include the trigger and key move columns for each shape.
Agent list: Run tools/genius-invoker.sh list --shapes. Format as a clean table with agent name, description, and shapes.
Pairs: Read the specified agent file at agents/genius/<agent>.md. Extract the pairs_well_with frontmatter field. For each paired agent, show its description. Suggest composition patterns using /genius-compose.
Search: Run tools/genius-invoker.sh list --search "<term>". Also search INDEX.md for matching shapes. Combine results, deduplicating by agent name.
Always end with a usage hint: how to invoke an agent (/genius-invoke <name> "<problem>"), how to compose agents (/genius-compose), or how to let the router pick (/genius-route).

$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.

2d ago First seen · 33 lines · 0 tokens per session scan A 99557b966982

Subscribe to this mod's changes

index is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 462 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.

Data and AI Databases Research bm25 claude-code claude-code-plugin clean-architecture code-graph code-intelligence

index

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Genius Agent Index

Instructions

What this file has done since we first saw it

Other commands, from other repositories

brooks-audit

brooks-health

daily-standup

deploy

fix-issue

simplify