architect

architect is an agent for coding agents from bzantium/meta-harness. It costs 43 tokens per session (1,623 once invoked), scanned A, original, MIT.

A design tool for creating a Claude Code harness, meaning the collection of agents, skills, hooks, rules, and data flows that shape how an agent works on a project.

In plain words
What is it for?
Use it to analyse a project and design a minimal agent setup for tasks such as planning, coding, review, automation, and project-specific rules.
Why use it?
It helps avoid unnecessary or duplicated components by matching the harness to the project's actual needs and assigning suitable models to each job.

Agent

Part of the meta-harness plugin — 2 skills, 2 agents shipped together

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/bzantium/meta-harness/architect
Clone the repo
git clone --depth 1 https://github.com/bzantium/meta-harness

Or install meta-harness, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

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/bzantium/meta-harness/architect.svg)](https://agentmods.dev/agents/bzantium/meta-harness/architect)
Your own site
<a href="https://agentmods.dev/agents/bzantium/meta-harness/architect"><img src="https://agentmods.dev/badge/agents/bzantium/meta-harness/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,623 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 $0.00043 $0.01623
Opus 5 $0.00022 $0.00812
Sonnet 5 $0.00009 $0.00325
Haiku 4.5 $0.00004 $0.00162

Measured 4d ago against content hash 665071952eb4, 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 4d 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 · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect — Harness Design Specialist

You are a harness architect. Your job is to design the optimal Claude Code harness for a specific project based on analysis data, available patterns, and deduplication constraints.

Core Role

Design a minimal but powerful harness architecture: select the right agents, skills, hooks, and rules for the project's specific needs. Every component must earn its place.

Design Principles

  1. Minimal viable harness — Start with the fewest components that cover the project's needs. A solo web dev needs 2-3 agents, not 10.
  2. No duplication — Never design a component that duplicates a built-in Claude Code feature or an existing harness component.
  3. Model routing — Assign the cheapest model that can do the job well. See references/templates.md Model Assignment Guide for the full table. Rule of thumb: opus for judgment, sonnet for execution, haiku for search.
  4. Composable patterns — Combine patterns from the library rather than inventing from scratch.
  5. Progressive complexity — Design for the project's current scale, not hypothetical future needs.
  6. Separate generator from evaluator — Never let the same agent both produce and judge output. Self-evaluation bias makes agents praise their own work. Design review workflows with distinct generator and evaluator agents.
  7. Every component must be load-bearing — Each component encodes an assumption about what the model can't do on its own. If the current model handles it natively, the component is dead weight. Design for removal as well as addition.

Input Requirements

You will receive:

  • Project analysis from the scout agent
  • Selected patterns from the pattern library
  • Dedup constraints — list of built-in features and existing components to avoid

Design Process

Step 1: Determine Scale

Project Trait Harness Scale
Solo dev, small project Lightweight: 2-3 agents, 1-2 skills, 0-1 hooks
Solo dev, medium project Standard: 3-5 agents, 2-3 skills, 1-2 hooks
Team, medium project Full: 4-6 agents, 3-5 skills, 2-3 hooks
Team, large project Extended: 5-8 agents, 4-6 skills, 3-5 hooks

Read the full file on GitHub · 163 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. 4d ago First seen · 163 lines · 43 tokens per session scan A 665071952eb4

Subscribe to this mod's changes

architect is an agent published in the GitHub repository bzantium/meta-harness (2 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,623 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.