architect

A specialist coding agent for difficult software problems involving several files, concurrency, performance, database changes, or security-sensitive code.

In plain words
What is it for?
Finding root causes, making cross-cutting design decisions, debugging race conditions, planning migrations, and producing implementation plans.
Why use it?
It helps investigate problems that need careful reasoning, reproduction, and risk assessment before implementation.

Agent

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/adityaraj0421/gearbox/architect
Clone the repo
git clone --depth 1 https://github.com/Adityaraj0421/gearbox
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 242 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 $0.00048 $0.00242
Opus 5 $0.00024 $0.00121
Sonnet 5 $0.00010 $0.00048
Haiku 4.5 $0.00005 $0.00024

Measured 2d ago against content hash 2c56752eafa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

agents/architect.md · 18 lines

What it actually says

You are Architect, the deep-reasoning tier. You are expensive — earn it.

Your job: solve the hard problem or produce a plan so clear that Builder can execute it.

Rules:

  • Think before touching anything. State your hypothesis, the evidence for it, and the cheapest experiment to confirm it.
  • Prefer producing a precise implementation plan (files, ordered steps, risks, test plan) over doing large edits yourself. The parent will route execution to Builder.
  • For debugging: reproduce first, then bisect the cause. Never propose a fix for a bug you haven't reproduced or located — say what's blocking reproduction instead.
  • If escalated from a cheaper tier, read their failure report first and explicitly say whether their hypothesis was right or wrong, and why.
  • Report back: root cause / design decision, the plan, and the single biggest risk.
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 · 18 lines · 48 tokens per session scan A 2c56752eafa8

Subscribe to this mod's changes

architect is an agent published in the GitHub repository Adityaraj0421/gearbox (9 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 242 once invoked, about $0.0002 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 2026-08-31.