init-harness

init-harness is a skill for Claude Code from adrielp/ai-engineering-harness. It costs 34 tokens per session (1,154 once invoked), scanned A, original, Apache-2.0.

A repository setup guide for an AI engineering harness, a set of files and conventions that gives coding agents project context. It creates an AGENTS.md file, a thoughts directory, and a ticket template.

In plain words
What is it for?
Use it when preparing a repository for AI-assisted development or initializing its context-engineering structure.
Why use it?
It gives AI-assisted development work a consistent place for repository instructions, planning notes, and tickets.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Good fit Use it when preparing a repository for AI-assisted development or initializing its context-engineering structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adrielp/ai-engineering-harness/init-harness
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.

Any agent
npx skills add adrielp/ai-engineering-harness --skill init-harness
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

Made for: Claude Code.

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 init-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/init-harness/github.svg)](https://agentmods.dev/skills/adrielp/ai-engineering-harness/init-harness)
Your own site
<a href="https://agentmods.dev/skills/adrielp/ai-engineering-harness/init-harness"><img src="https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/init-harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for init-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/adrielp/ai-engineering-harness/init-harness"><img src="https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/init-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.01154
Opus 5 $0.00017 $0.00577
Sonnet 5 $0.00007 $0.00231
Haiku 4.5 $0.00003 $0.00115

Measured 7d ago against content hash f579fa68f50a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

init-harness 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 7d 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.

pi/skills/init-harness/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize AI Engineering Harness

When to Use This Skill

Activate when the user:

  • Runs /init_harness
  • Asks to "initialize the harness" / "set up the harness" / "set up context engineering"
  • Wants to prepare a repository for AI-assisted development workflows

What This Skill Does

  1. Runs the built-in /init command to generate AGENTS.md
  2. Creates the thoughts/ directory structure for context engineering
  3. Adds a ticket template for consistent ticket creation
  4. Provides guidance on next steps

Core Process

Step 1: Check Current State

test -f AGENTS.md && echo "AGENTS.md exists" || echo "AGENTS.md not found"
test -d thoughts && echo "thoughts/ exists" || echo "thoughts/ not found"
test -d .git && echo "Git repo" || echo "Not a git repo"

Step 2: Run /init Command

If AGENTS.md doesn't exist (or the user wants to regenerate), invoke the built-in /init command. It analyzes the codebase structure, identifies key components and patterns, and writes AGENTS.md with codebase context. Then confirm:

test -f AGENTS.md && echo "AGENTS.md created successfully"

Step 3: Create Thoughts Directory Structure

mkdir -p thoughts/shared/{tickets,plans,research}
mkdir -p thoughts/global

Directory purposes:

thoughts/
├── shared/           # Team-shared documents
│   ├── tickets/      # Feature requests, bugs, task definitions
│   ├── plans/        # Implementation plans (via /create_plan)
│   └── research/     # Research documents and investigations
├── global/           # Cross-repository concerns and docs
└── {username}/       # Personal notes (optional, Step 6)

Step 4: Add Ticket Template

Create thoughts/shared/tickets/ticket-template.md if it doesn't already exist:

test -f thoughts/shared/tickets/ticket-template.md || echo "Creating ticket template..."

Write the template using the structure in the ticket template — a markdown skeleton with Problem Statement, Desired Outcome, Context & Background, Requirements, Acceptance Criteria (automated + manual verification), Technical Notes, and a Meta block.

Read the full file on GitHub · 122 lines

Files

What ships with it

1 file 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. 7d ago First seen · 122 lines · 34 tokens per session scan A f579fa68f50a

Subscribe to this mod's changes

init-harness is a skill published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,154 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens