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 skills add thaifurforo/ai-toolkit --skill harness-engineeringgit clone --depth 1 https://github.com/thaifurforo/ai-toolkitWrote 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/skills/thaifurforo/ai-toolkit/harness-engineering)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-engineering"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-engineering.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 5.1 | $0.00213 | $0.03324 |
| Opus 5 | $0.00106 | $0.01662 |
| Sonnet 5 | $0.00043 | $0.00665 |
| Haiku 4.5 | $0.00021 | $0.00332 |
Grade A, and why
harness-engineering 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering
"O gargalo nunca foi a capacidade do agente de escrever código — foi a falta de estrutura, ferramentas e mecanismos de feedback ao seu redor." — OpenAI Engineering Blog, 2026
Pipeline de desenvolvimento com IA que transforma uma ideia em software confiável, combinando guias (feedforward) e sensores (feedback) que permitem autocorreção antes de chegar ao humano.
Modelo mental: Guias + Sensores
Guias (feedforward — antes de agir):
- O agente tem o contexto certo? (PRD, arquitetura, convenções)
- As restrições estão codificadas? (linters, tipos, estrutura de camadas)
- A documentação existe como sistema de record? (
.catalog/,AGENTS.md, tracking configurado)
Sensores (feedback — após agir):
- Computacionais: testes, linters, type check, análise estrutural (rápidos, determinísticos)
- Inferenciais: code review por IA, "LLM como juiz" (mais lentos, semânticos)
Regra: sensores computacionais rodam a cada commit. Sensores inferenciais rodam antes do PR e no pipeline.
Sistema de IDs — fio de rastreabilidade
RF-01 (PRD) → US-01 (story) → CA-01 (critério) → T-01 (task) → teste que verifica CA-01
Nunca crie tasks sem RF. Nunca feche task sem gate verificado. Nunca abra PR sem CA validados.
Tracking e release são eixos separados
Leia project_tracking.tool e release_management.strategy em harness.config.yaml antes de criar documentação, issues, milestones, changelog ou release notes.
| Eixo | Campo | Valores suportados | Decide |
|---|---|---|---|
| Gestão de projeto | project_tracking.tool |
github, jira, linear, azuredevops, local |
Onde vivem PRD, agrupamentos, user stories, tasks e status |
| Versionamento de release | release_management.strategy |
github-auto-release, github-legacy, release-please, manual-changelog, none |
Como versionar, gerar changelog e publicar releases |
Presets como github-auto-release e github-legacy são atalhos que preenchem os dois eixos quando o usuário quiser GitHub para tudo. Eles não impedem combinações como project_tracking.tool: jira + release_management.strategy: github-auto-release.
What ships with it
5 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.
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.
- 7d ago First seen · 260 lines · 213 tokens per session scan A 2d51da9312f5
harness-engineering is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 213 tokens to every session and 3,324 once invoked, about $0.0011 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…