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.
npx agentmods add commands/cdeust/ai-architect-mcp-codebase/invokegit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00306 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
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.
What it actually says
Invoke Genius Agent
Load a genius agent by name and apply its reasoning pattern to a problem inline.
Instructions
-
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" -
Run
tools/genius-invoker.sh invoke <agent-name> "<problem>"to validate the agent exists and load its content. -
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
- The
-
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.
-
Produce output in the agent's
output-format. If the agent defines a specific structure (sections, tables, verdicts), follow it exactly. -
If the agent's workflow calls for tools (difficulty books, provenance files, estimates), use the corresponding tools from
tools/. -
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_withfrontmatter field).
$ARGUMENTS
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 · 26 lines · 0 tokens per session scan A 433bffe34572
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.
Other commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
brooks-health
Run a Brooks-Lint codebase health dashboard across all four dimensions.
daily-standup
Génération Résumé Daily Stand-up.
deploy
Build, test, deploy with staged rollout.
fix-issue
Analyze and fix a reported bug or issue systematically.
simplify
Reduce complexity without changing behavior — code simplification.