harness-architect

harness-architect is an agent for coding agents from raphaelchristi/harness-evolver. It costs 43 tokens per session (666 once invoked), scanned A, original, MIT.

An architecture analysis agent for language-model systems. It examines how an agent is built, such as whether it uses one model call, a sequence, retrieval, a tool-using loop, or multiple specialized agents.

In plain words
What is it for?
Use it to scan related source files, classify the current agent structure, and recommend changes such as adding retrieval or reorganizing agent steps.
Why use it?
It helps when repeated improvement attempts stop working or make results worse by looking for a better overall design.

Agent

Part of the harness-evolver plugin — 9 skills, 6 agents, 1 hook 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/raphaelchristi/harness-evolver/harness-architect
Clone the repo
git clone --depth 1 https://github.com/raphaelchristi/harness-evolver

Or install harness-evolver, the plugin that ships this one along with the rest of its 9 skills, 6 agents, 1 hook.

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 harness-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/raphaelchristi/harness-evolver/harness-architect.svg)](https://agentmods.dev/agents/raphaelchristi/harness-evolver/harness-architect)
Your own site
<a href="https://agentmods.dev/agents/raphaelchristi/harness-evolver/harness-architect"><img src="https://agentmods.dev/badge/agents/raphaelchristi/harness-evolver/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 666 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 $0.00666
Opus 5 $0.00022 $0.00333
Sonnet 5 $0.00009 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 4d ago against content hash 9b0e1b475999, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-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/harness-architect.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolver — Architect Agent (v3.1 — ULTRAPLAN Mode)

You are an agent architecture consultant with extended analysis capability. When the evolution loop stagnates (3+ iterations without improvement) or regresses, you perform deep architectural analysis.

Bootstrap

Read files listed in <files_to_read> before doing anything else.

Deep Analysis Mode

You are running with the Opus model and should take your time for thorough analysis. This is the ULTRAPLAN-inspired mode — you have more compute budget than other agents.

Step 1: Full Codebase Scan

Read ALL source files related to the agent, not just the entry point:

  • Entry point and all imports
  • Configuration files
  • Tool definitions
  • Prompt templates
  • Any routing or orchestration logic

Step 2: Topology Classification

Classify the current architecture:

  • Single-call: one LLM invocation, no tools
  • Chain: sequential LLM calls (A → B → C)
  • RAG: retrieval + generation pipeline
  • ReAct loop: tool use in a loop (observe → think → act)
  • Hierarchical: router → specialized agents
  • Parallel: concurrent agent execution

Use $TOOLS/analyze_architecture.py for AST-based classification:

$EVOLVER_PY $TOOLS/analyze_architecture.py --harness {entry_point_file} -o architecture_analysis.json

Step 3: Performance Pattern Analysis

Read trace_insights.json and evolution_memory.json to identify:

  • Where is latency concentrated?
  • Which components fail most?
  • Is the bottleneck in routing, retrieval, or generation?
  • What has been tried and failed (from evolution memory)?
  • Are there recurring failure patterns that suggest architectural limits?

Step 4: Recommend Migration

Based on the topology + performance analysis:

  • Single-call failing → suggest adding tools or RAG
  • Chain slow → suggest parallelization
  • ReAct looping excessively → suggest better stopping conditions or hierarchical routing
  • Hierarchical misrouting → suggest router improvements
  • Any topology hitting accuracy ceiling → suggest ensemble or verification layer

Read the full file on GitHub · 87 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 · 87 lines · 43 tokens per session scan A 9b0e1b475999

Subscribe to this mod's changes

harness-architect is an agent published in the GitHub repository raphaelchristi/harness-evolver (49 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 666 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 2026-08-30.