agentmods.dev

learn-harness-engineering CLAUDE.md

learn-harness-engineering CLAUDE.md is an instructions file for coding agents from walkinglabs/learn-harness-engineering. It costs 776 tokens per session, scanned A, original, MIT.

Project instructions for Learn Harness Engineering, a course about building reliable coding environments for AI agents. They describe the repository, its VitePress documentation site, and its example Electron applications.

In plain words
What is it for?
Use them when working on the course documentation, building or previewing the site, or checking and testing its Electron project examples.
Why use it?
They give Claude Code consistent commands and project context, reducing mistakes when editing documentation or running the course examples.

Instructions file

not rated 15k +123 9d ago A scan 776 tokens original MIT
View the source file walkinglabs/learn-harness-engineering
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 instructions/walkinglabs/learn-harness-engineering/claude-md
Clone the repo
git clone --depth 1 https://github.com/walkinglabs/learn-harness-engineering

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 learn-harness-engineering CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/walkinglabs/learn-harness-engineering/claude-md.svg)](https://agentmods.dev/instructions/walkinglabs/learn-harness-engineering/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/walkinglabs/learn-harness-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/walkinglabs/learn-harness-engineering/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 776 This file is loaded in full into every session.
When invoked 776 The same file — it is already loaded in full.
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 $0.00776 $0.00776
Opus 5 $0.00388 $0.00388
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00078 $0.00078

Measured 4d ago against content hash b5a3ee4fdd55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-harness-engineering CLAUDE.md 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.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Learn Harness Engineering is a project-based course on building reliable coding environments for AI agents. The repo contains a VitePress documentation site plus hands-on project code.

Commands

# Documentation site
npm install
npm run docs:dev        # Dev server with hot reload (VitePress)
npm run docs:build      # Production build
npm run docs:preview    # Preview built site

# Run lecture code examples
npx tsx docs/en/lectures/<lecture-dir>/code/<file>.ts

# Project Electron apps (from each project directory)
cd projects/project-NN/starter  # or solution/
npm install
npm run dev              # Build + launch Electron (via scripts/dev.js)
npm run check            # Type-check both tsconfig.json and tsconfig.node.json
npm run test             # Vitest run (single run)
npm run test:watch       # Vitest watch mode

Repository Structure

  • docs/ — VitePress documentation site (lectures, projects, resources)
  • docs/.vitepress/config.mts — Nav/sidebar config for all 15 locales (en, zh, zh-TW, ja, ko, es, fr, ru, de, ar, vi, uz, tr, uk, pt-BR)
  • docs/<lang>/lectures/ — 14 lectures, each with index.md + code/ examples
  • docs/<lang>/projects/ — 8 project descriptions
  • docs/<lang>/resources/ — localized templates, references, OpenAI advanced pack
  • docs-readme/ — localized README translations (one directory per locale)
  • projects/shared/ — Shared Electron + TypeScript + React foundation
  • projects/project-NN/ — Per-project starter/ and solution/ directories (project-01 through project-06; project-07 and project-08 are docs-only so far)

Architecture

The course revolves around an Electron knowledge-base desktop app that evolves across the projects:

  • Main process (src/main/): Window management, IPC handlers, service initialization
  • Preload (src/preload/): contextBridge exposing typed API to renderer
  • Renderer (src/renderer/): React UI with document list, Q&A panel, status bar
  • Services (src/services/): DocumentService, IndexingService, QaService, PersistenceService
  • Shared types (src/shared/types.ts): Cross-boundary interfaces and IPC channel constants

Read the full file on GitHub · 64 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 · 64 lines · 776 tokens per session scan A b5a3ee4fdd55

Subscribe to this mod's changes

learn-harness-engineering CLAUDE.md is an instructions file published in the GitHub repository walkinglabs/learn-harness-engineering (14,742 stars, last pushed 9d ago), licensed MIT. It adds 776 tokens to every session, about $0.0039 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.

LLMagentaiharnessharness-engineeringharness-framework
Related

Other instructions, from other repositories

trueforge AGENTS.md

AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.

truefoundry/trueforge · 1,259 tokens

sprawling AGENTS.md

Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.

2youg1/sprawling · 2,019 tokens

opencode-plusplus AGENTS.md

Instructions for whut09/opencode-plusplus, covering agent guide, generated agent guide, must-read rules, default workflow and project entrypoints.

whut09/opencode-plusplus · 1,250 tokens

sprawling CLAUDE.md

Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.

2youg1/sprawling · 83 tokens

duet-agent AGENTS.md

AGENTS.md instructions for dzhng/duet-agent, covering agent guidelines, treat types as documentation, keep names current, keep comments useful and prefer direct, local guarantees.

dzhng/duet-agent · 1,591 tokens

trueforge CLAUDE.md

Claude Code instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.

truefoundry/trueforge · 5 tokens