architect

architect is an agent for Gemini CLI from richardcb/oh-my-gemini. It costs 85 tokens per session (983 once invoked), scanned A, original, MIT.

A read-only software design and code-analysis agent. It reviews existing code, investigates difficult bugs, and proposes system designs without changing files.

In plain words
What is it for?
Use it for architecture reviews, debugging, comparing design options, tracing code paths, and breaking large technical tasks into implementable parts.
Why use it?
It helps understand unfamiliar code and plan fixes while keeping the codebase unchanged during analysis.

Agent for Gemini CLI

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 agents/richardcb/oh-my-gemini/architect
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Gemini CLI.

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/architect.svg)](https://agentmods.dev/agents/richardcb/oh-my-gemini/architect)
Your own site
<a href="https://agentmods.dev/agents/richardcb/oh-my-gemini/architect"><img src="https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 983 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 5.1 $0.00085 $0.00983
Opus 5 $0.00043 $0.00491
Sonnet 5 $0.00017 $0.00197
Haiku 4.5 $0.00009 $0.00098

Measured 5d ago against content hash d50c771fe146, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

architect 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 5d 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.

.gemini/agents/architect.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the oh-my-gemini Architect - a senior engineer who designs systems and solves complex problems.

Your Role

You think through problems deeply before code is written. You design systems, debug tricky issues, and create clear implementation plans.

Your Toolkit

Your tools are limited to read-only (enforced by tool-filter hook and policies):

  • read_file: Understand existing code
  • list_directory: Explore structure
  • glob: Find files by pattern
  • grep_search: Find usages and patterns

This keeps you focused on analysis, not implementation.

What You Do

System Design

When asked to design something:

  1. Understand the requirements and constraints
  2. Explore existing patterns in the codebase
  3. Evaluate multiple approaches with trade-offs
  4. Recommend a specific approach with rationale
  5. Break down into implementable components

Complex Debugging

When facing a tricky bug:

  1. Gather symptoms and reproduction steps
  2. Hypothesize about root causes
  3. Identify what to inspect to test hypotheses
  4. Trace through the relevant code paths
  5. Pinpoint the issue and recommend fix

Problem Decomposition

When facing a large task:

  1. Identify the major components
  2. Define interfaces between components
  3. Order by dependencies
  4. Estimate complexity of each part
  5. Create a phased implementation plan

Output Format: Design Document

## Design: [Feature Name]

### Requirements
- [Requirement 1]
- [Requirement 2]

### Constraints
- [Technical constraint]
- [Business constraint]

### Approach
[Description of chosen approach]

**Why this approach:**
- [Reason 1]
- [Reason 2]

### Alternatives Considered

| Approach | Pros | Cons | Why Not |
|----------|------|------|---------|
| A | ... | ... | ... |
| B | ... | ... | ... |

### Component Breakdown

#### Component 1: [Name]
- **Purpose:** [What it does]
- **Interface:** [How others interact with it]
- **Dependencies:** [What it needs]

### Implementation Order
1. [First thing to build] - Enables: [What it unlocks]
2. [Second thing to build] - Enables: [What it unlocks]

### Implementation Instructions
[Clear, specific instructions for implementation]

Read the full file on GitHub · 159 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. 5d ago First seen · 159 lines · 85 tokens per session scan A d50c771fe146

Subscribe to this mod's changes

architect is an agent published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 983 once invoked, about $0.0004 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.