harness-studio AGENTS.md

harness-studio AGENTS.md is an instructions file for Codex, OpenCode from almond-bot/harness-studio. It costs 263 tokens per session, scanned A, original, MIT.

Repository instructions for Almond Harness Studio, a tool that designs electrical wire harnesses—bundles of wires and connectors—as JSON files and exports PDF drawings for manufacturers. They define the project’s TypeScript, workspace, validation, and example conventions.

In plain words
What is it for?
Use them to design, document, validate, price, or export wire harnesses, cable assemblies, and pigtails. The instructions cover creating the JSON file, fetching component data, and exporting a PDF.
Why use it?
They provide the required format and checks for harness designs and ensure that listed parts can be traced to real distributor part numbers. This reduces errors before a drawing is sent for manufacturing or quoting.

Instructions file for CodexOpenCode

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/almond-bot/harness-studio/agents-md
Clone the repo
git clone --depth 1 https://github.com/almond-bot/harness-studio

Made for: Codex, OpenCode.

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-studio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/almond-bot/harness-studio/agents-md.svg)](https://agentmods.dev/instructions/almond-bot/harness-studio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/almond-bot/harness-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/almond-bot/harness-studio/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 263 This file is loaded in full into every session.
When invoked 263 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 $0.00263 $0.00263
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 4d ago against content hash 503dc6fd81b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-studio AGENTS.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.

AGENTS.md · 19 lines

What it actually says

AGENTS.md

Wire harness drawings

This project uses almond-harness-studio to design wire harnesses as JSON and export manufacturer-ready PDF drawings.

When asked to design, draw, document, or quote a wire harness, cable assembly, or pigtail, follow the instructions in skill/SKILL.md. In short:

  1. Author <name>.harness.json (schema guide: skill/reference.md, examples: skill/examples/). Components must reference real LCSC/Mouser/Digi-Key part numbers.
  2. npx almond-harness-studio validate <file> and fix all errors
  3. npx almond-harness-studio parts fetch <file> to embed distributor data (LCSC needs no API key)
  4. npx almond-harness-studio export <file> -o <file>.pdf

Repo conventions

  • TypeScript, double quotes, npm workspaces (packages/core, packages/app, packages/cli)
  • npm run build builds everything; npm run dev starts the viewer against examples/
  • npm run check:examples must pass; run it after changing the schema, validator, or examples
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 · 19 lines · 263 tokens per session scan A 503dc6fd81b1

Subscribe to this mod's changes

harness-studio AGENTS.md is an instructions file published in the GitHub repository almond-bot/harness-studio (5 stars, last pushed 1mo ago), licensed MIT. It adds 263 tokens to every session, about $0.0013 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.

Related

Other instructions, from other repositories

URDF-Studio CLAUDE.md

Claude Code instructions for OpenLegged/URDF-Studio, covering urdf studio agent guide, 语言偏好, 需求澄清与第一性原理, src/ 目录结构 and scripts/ 目录结构.

OpenLegged/URDF-Studio · 8,074 tokens

fusion360-mcp-server AGENTS.md

Instructions for faust-machines/fusion360-mcp-server, covering agents.md, how the system works, available tools (80), scene & query and sketching.

faust-machines/fusion360-mcp-server · 2,497 tokens

rvt-mcp AGENTS.md

Instructions for bimwright/rvt-mcp, covering agents.md — rvt-mcp install guide for ai agents, rules for agents, baked-tool routing, prerequisites (check first, stop if any are missing) and step 1 — download the client setup zip.

bimwright/rvt-mcp · 3,721 tokens

cad-cae-copilot copilot-instructions.md

Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.

armpro24-blip/cad-cae-copilot · 323 tokens

elements CLAUDE.md

Claude Code instructions for NVIDIA/elements, a project described as: NVIDIA Design System and UI Agent Harness for AI/ML Factories, Robotics, and Autonomous Vehicles.

NVIDIA/elements · 3 tokens

openscad-mcp GEMINI.md

Gemini CLI instructions for rahulgarg123/openscad-mcp: You are an expert CAD modeler adept at writing OpenSCAD code. The user will ask you to generate openSCAD code by providing text instruction and / or a rough sketch. Follow the following steps to process user's request.

rahulgarg123/openscad-mcp · 432 tokens