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-documentationgit 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-documentation)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-documentation"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-documentation.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 | $0.00059 | $0.00820 |
| Opus 5 | $0.00030 | $0.00410 |
| Sonnet 5 | $0.00012 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
harness-documentation 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness: Documentação (Etapa 07)
Persona: Technical writer.
Duas Camadas — Responsabilidades Distintas
.catalog/ ← fonte de verdade técnica (versionada no repositório)
architecture.md, conventions.md, concerns.md, features.md, stack.md...
[delivery_docs.path]/ ← docs de entrega quando `project_tracking.tool: local` ou fallback (padrão: .milestones/)
Ferramenta de rastreamento ← issues/cards/epics/stories conforme project_tracking.tool
Regra: AGENTS.md é a tabela de roteamento (≤100 linhas) — aponta para .catalog/ e para os itens de rastreamento.
Tipo A — Docs de Entrega (atualizar quando forem a fonte ativa)
Após cada [level2] concluída, atualizar estes arquivos quando project_tracking.tool: local ou quando uma ferramenta externa caiu para fallback markdown:
[delivery_docs.path]/[level1-nome]/[level2-XX]/changelog.md— o que mudou, por quê, impacto[delivery_docs.path]/[level1-nome]/[level2-XX]/tech-spec.md— marcar tasks completas, atualizar status para ✅[delivery_docs.path]/[level1-nome]/[level1].md— marcar [level2] completa
Fechar entrega conforme project_tracking.tool — ver references/11-project-tracking.md. Não duplique docs locais se GitHub/Jira/Linear/Azure DevOps é a fonte de verdade ativa e conectada.
Tipo B — Docs de Contexto (atualizar APENAS se algo mudou)
Atualizar somente quando a US introduziu algo novo:
| Arquivo | Quando atualizar |
|---|---|
.catalog/features.md |
Nova funcionalidade implementada |
.catalog/architecture.md |
Novo ADR, mudança de camada, padrão estrutural |
.catalog/conventions.md |
Novo padrão de código emergiu |
.catalog/concerns.md |
Nova dívida técnica ou risco |
.catalog/stack.md |
Nova dependência ou configuração |
Jamais delete ADRs — são a memória histórica do projeto.
Changelog e Release Notes
| Situação | Abordagem |
|---|---|
release_management.strategy: github-auto-release |
Label release:* no PR e release notes geradas pelo workflow |
release_management.strategy: github-legacy |
Milestone versionada apenas se configurada; release notes conforme convenção |
release_management.strategy: release-please |
Conventional Commits → geração automática de CHANGELOG.md e Release |
release_management.strategy: manual-changelog |
Manter CHANGELOG.md ou changelog de entrega manual |
release_management.strategy: none |
Não criar changelog/release formal |
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.
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 · 70 lines · 59 tokens per session scan A 5b18452b262b
harness-documentation is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 820 once invoked, about $0.0003 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…