invoke

A command for loading a named reasoning guide and applying its instructions to a problem. The guide defines the reasoning method and the format of the answer.

In plain words
What is it for?
Use it to run a named genius agent on a problem, following that agent's workflow and requested output format.
Why use it?
It avoids manually finding and following the right reasoning guide for each problem.

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/invoke
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 306 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 $0.00306
Opus 5 $0.00000 $0.00153
Sonnet 5 $0.00000 $0.00061
Haiku 4.5 $0.00000 $0.00031

Measured 2d ago against content hash 433bffe34572, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

invoke 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/invoke.md · 26 lines

What it actually says

Invoke Genius Agent

Load a genius agent by name and apply its reasoning pattern to a problem inline.

Instructions

  1. Parse $ARGUMENTS: the first word is the agent name, the rest is the problem description. Example: /genius-invoke darwin "Our metrics show a slow decline but we keep theorizing before we have enough data"

  2. Run tools/genius-invoker.sh invoke <agent-name> "<problem>" to validate the agent exists and load its content.

  3. Read the full agent file at agents/genius/<name>.md. Pay attention to:

    • The <identity> section for the reasoning pattern
    • The <workflow> section for the step-by-step procedure
    • The <output-format> section for how to structure the response
  4. Apply the agent's workflow to the problem. Work through each step of the agent's procedure, applying it to the specific problem described. Do not skip steps.

  5. Produce output in the agent's output-format. If the agent defines a specific structure (sections, tables, verdicts), follow it exactly.

  6. If the agent's workflow calls for tools (difficulty books, provenance files, estimates), use the corresponding tools from tools/.

  7. End with a "Next step" recommendation: what the user should do next, and whether another genius agent should be consulted (check the agent's pairs_well_with frontmatter field).

$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 · 26 lines · 0 tokens per session scan A 433bffe34572

Subscribe to this mod's changes

invoke 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 306 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.