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.
npx agentmods add instructions/adrielp/ai-engineering-harness/agents-mdgit clone --depth 1 https://github.com/adrielp/ai-engineering-harnessWrote 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.
[](https://agentmods.dev/instructions/adrielp/ai-engineering-harness/agents-md)<a href="https://agentmods.dev/instructions/adrielp/ai-engineering-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/adrielp/ai-engineering-harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01784 | $0.01784 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
ai-engineering-harness 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineering Harness
For AI Agents: This document provides structured reference data for AI coding assistants. For human-readable documentation, see README.md.
Quick Reference
Purpose: Configuration harness for AI coding agents with reusable prompts, agents, and workflows.
Supported Tools: OpenCode, Claude Code, Gemini CLI, Pi
Installation: ./setup.sh <tool> where tool is opencode, claude, gemini, pi, or all
Repository Structure
ai-engineering-harness/
├── opencode/ → ~/.config/opencode/
│ ├── agents/ # 6 agents (snake_case)
│ ├── commands/ # 11 slash commands
│ ├── skills/ # 15 skills (auto-triggered)
│ └── opencode.json # MCP configuration
├── claude/ → ~/.claude/
│ ├── agents/ # 6 agents (snake_case)
│ ├── skills/ # 26 skills (13 manual + 13 auto)
│ ├── .mcp.json # MCP configuration
│ └── settings.json # Settings schema
├── gemini/ → ~/.gemini/
│ ├── agents/ # 6 agents (snake_case)
│ ├── commands/ # 14 commands (TOML format)
│ └── skills/ # 23 skills (auto-triggered)
├── pi/ → ~/.pi/agent/
│ ├── agents/ # 6 agents (kebab-case)
│ ├── prompts/ # 11 prompt templates (Pi's commands)
│ ├── skills/ # 21 skills (auto-triggered)
│ └── extensions/ # subagent extension (multi-agent workflows)
└── thoughts/ # Context engineering artifacts
├── shared/tickets/ # Work items
├── shared/plans/ # Implementation plans
├── shared/research/# Research documents
└── global/ # Cross-repo concerns
Commands & Skills
| Command | OpenCode | Claude | Gemini | Pi | Type | Description |
|---|---|---|---|---|---|---|
/init_harness |
✓ | ✓ | ✓ | ✓ | Manual | Initialize harness (creates AGENTS.md/CLAUDE.md/GEMINI.md + thoughts/) |
/create_plan |
✓ | ✓ | ✓ | ✓ | Manual | Generate implementation plan from ticket |
/implement_plan |
✓ | ✓ | ✓ | ✓ | Manual | Execute approved plan phase-by-phase |
/validate_plan |
✓ | ✓ | ✓ | ✓ | Manual | Verify implementation against plan |
/commit |
✓ | ✓ | ✓ | ✓ | Manual | Create well-structured git commits |
/debug |
✓ | ✓ | ✓ | ✓ | Manual | Investigate issues during testing |
/debug_k8s |
✓ | ✓ | ✓ | ✓ | Manual | Debug Kubernetes (prefers MCP, falls back to kubectl) |
/research_codebase |
✓ | ✓ | ✓ | ✓ | Manual | Comprehensive codebase research |
/validate_telemetry |
✓ | ✓ | ✓ | ✓ | Manual | Validate local telemetry against a narrative spec |
observability_driven_development |
✓ | ✓ | ✓ | ✓ | Auto | Design the trace before the feature; local OTel feedback loop |
git_commit_helper |
✓ | ✓ | ✓ | ✓ | Auto | Triggers on "commit" keywords |
pr_description_generator |
✓ | ✓ | ✓ | ✓ | Auto | Triggers when creating PRs |
experimental_pr_workflow |
✓ | ✓ | ✓ | ✓ | Auto | Formalizes experimental work |
interview |
✓ | ✓ | ✓ | ✓ | Auto | Stress-test plans via relentless user interview |
improve_codebase_architecture |
✓ | ✓ | ✓ | ✓ | Auto | Find architectural friction, propose deep-module refactors |
prd_to_issues |
✓ | ✓ | ✓ | ✓ | Auto | Break a PRD into vertical-slice issue files |
tdd |
✓ | ✓ | ✓ | ✓ | Auto | Red-green-refactor TDD discipline |
write_a_prd |
✓ | ✓ | ✓ | ✓ | Auto | Generate a PRD from a client brief |
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.
- 4d ago First seen · 134 lines · 1,784 tokens per session scan A f51684598ebe
ai-engineering-harness AGENTS.md is an instructions file published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,784 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.