harness-setup

harness-setup is a skill for Claude Code, Codex from ShipWithAI/shipwithai-plugins. It costs 43 tokens per session (1,200 once invoked), scanned A, original, MIT.

A setup tool that examines a project's actual files and creates instructions, permissions, and safety hooks for Claude Code. A harness is the project configuration that guides the coding assistant and limits risky actions.

In plain words
What is it for?
Use it to create or refresh CLAUDE.md, settings.json, validate-command.py, and protect-files.py for almost any project stack.
Why use it?
It avoids generic setup by basing the generated files on the project's language, build tools, source structure, and tests. It also checks before replacing an existing CLAUDE.md.

Skill for Claude CodeCodex

Part of the shipwithai-harness plugin — 2 skills 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 skills/shipwithai/shipwithai-plugins/harness-setup
Any agent
npx skills add ShipWithAI/shipwithai-plugins --skill harness-setup
Clone the repo
git clone --depth 1 https://github.com/ShipWithAI/shipwithai-plugins

Made for: Claude Code, Codex.

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

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-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/shipwithai/shipwithai-plugins/harness-setup.svg)](https://agentmods.dev/skills/shipwithai/shipwithai-plugins/harness-setup)
Your own site
<a href="https://agentmods.dev/skills/shipwithai/shipwithai-plugins/harness-setup"><img src="https://agentmods.dev/badge/skills/shipwithai/shipwithai-plugins/harness-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 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 $0.01200
Opus 5 $0.00022 $0.00600
Sonnet 5 $0.00009 $0.00240
Haiku 4.5 $0.00004 $0.00120

Measured 5d ago against content hash d94fc0ed66ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-setup 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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/hooks/protect-files.py, assets/hooks/validate-command.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/harness/skills/harness-setup/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Setup

Analyze your project and generate a production-ready Claude Code harness. Works for any stack — reads your actual code instead of filling templates.

When to Use

  • Project missing a CLAUDE.md, or existing one is generic/outdated
  • Need settings.json with balanced permission rules
  • Want validate-command.py + protect-files.py safety hooks

Step 0: Check for Existing CLAUDE.md

If CLAUDE.md exists and has content:

Ask: "Found existing CLAUDE.md. Overwrite with new harness, or skip?"

  • Skip → stop
  • Overwrite → continue

Step 1: Deep Project Scan (parallel reads)

Read references/analysis-guide.md for extraction instructions. Then run all reads simultaneously.

Read whichever of these exist:

  • Root config files: package.json, pom.xml, pyproject.toml, go.mod, Cargo.toml, composer.json, Gemfile, build.gradle
  • Makefile (if exists)
  • .env.example (if exists)
  • Directory structure: glob ** to depth 2
  • One representative source file (entry point or a typical service/controller)
  • One test file (look in tests/, test/, spec/, src/test/, __tests__/)

After reading, extract answers to:

Question Source
Stack Config files + deps (see analysis-guide.md §Stack Identification)
Run/build/test/lint commands scripts in package.json, Makefile targets, pom.xml goals
Directory structure Glob result — top 3–5 meaningful dirs
ORM/database Deps + schema file location
Env vars needed .env.example or grep process.env./os.getenv( in source
Test framework + location Test file imports + directory name
Package manager Lockfile presence: bun.lockb→bun, pnpm-lock.yaml→pnpm, yarn.lock→yarn, else npm
Port Dev script, application.properties:server.port, or stack default

Show summary before asking questions:

🔍 Scan complete

Stack:     Go (Gin framework)
Commands:  run: go run ./cmd/... | test: go test ./... | lint: golangci-lint run
Structure: cmd/, internal/, pkg/, migrations/
Database:  GORM — models in internal/models/
Tests:     Go testing (testify) in *_test.go files
Port:      8080
Env vars:  DATABASE_URL, JWT_SECRET, PORT

Read the full file on GitHub · 139 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 139 lines · 43 tokens per session scan A d94fc0ed66ad

Subscribe to this mod's changes

harness-setup is a skill published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 1,200 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.

Related

Other skills, from other repositories

claude-code-session-broker

Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.

Arch1eSUN/Arcgentic · 35 tokens

arcgentic

Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.

Arch1eSUN/Arcgentic · 43 tokens

espalier-migrate

Migrate an existing harness/espalier install to the current Espalier version — auto-detects which of v0.1→v0.2, v0.3→v0.4, v0.4→v0.5, the v0.5.3 coder-agent patch, v0.5→v0.6 (Stage 1 grill), v0.6→v0.7 (read-only /espalier-ask lane), v0.7→v0.8 (requirements approval gate), the v0.8.1 impact-analysis agent patch, the…

Junhanliu-dev/espalier-engineering · 0 tokens

verify-gates

Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…

Arch1eSUN/Arcgentic · 75 tokens

session-mode

Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.

Arch1eSUN/Arcgentic · 36 tokens

cross-session-handoff

Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.

Arch1eSUN/Arcgentic · 31 tokens