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-cicdgit 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-cicd)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-cicd"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-cicd/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.
<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-cicd"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-cicd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00721 |
| Opus 5.5 | $0.00026 | $0.00288 |
| Sonnet 5.5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
harness-cicd 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 13d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness: CI/CD e Sensores Contínuos (Etapa 09)
Persona: Engenheiro de DevOps / Platform Engineering.
Princípio Central: Shift-Left
Quanto mais cedo um sensor detecta um problema, mais barato é corrigir:
Custo de correção:
pre-commit < pre-push < CI por PR < pós-merge < produção
Arquitetura de Sensores (5 Camadas)
Camada 1 — Pré-commit (segundos): lint + type-check + testes unitários
Camada 2 — Pré-push (minutos): testes de integração + análise estrutural
Camada 3 — CI por PR (minutos): todas acima + security scan + build + AI review
Camada 4 — CI pós-merge: todas acima + mutation testing + arch review completo
Camada 5 — Agendado (semanal): código morto + docs obsoletas + audit de deps + PR de GC
Gates do Pipeline de CI (por PR)
gates:
- lint # falha rápida — antes de tudo
- type-check # idem
- unit-tests # com relatório de cobertura
- integration # com testcontainers ou DB em memória
- structural # dependency-cruiser / ArchUnit (violações de camada)
- security # npm audit / trivy
- build # artefato compilável
- review-agent # sensor inferencial (code review por IA)
Mensagens de erro do linter devem incluir instruções de remediação inline. Não apenas a violação — também como corrigir.
Estratégia de Deploy
| Evento | Ambiente | Ação |
|---|---|---|
PR apontando para main |
nonprd (staging) | Deploy automático |
Push para main |
produção | Deploy após aprovação manual |
| Deploy com falha | qualquer | Rollback automático + alerta |
Sensor de Garbage Collection (padrão OpenAI)
Workflow agendado semanalmente que:
- Escaneia código morto, testes redundantes, documentação obsoleta
- Abre PRs de limpeza automaticamente
- Mantém a dívida técnica como "pagamentos contínuos pequenos" em vez de grandes recessões
Endpoint de Healthcheck
// GET /health
{
status: "ok",
version: "1.2.0",
uptime: 3600,
dependencies: { database: "ok" }
}
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.
- 13d ago Changed d94e21d8012e
- 2mo ago First seen · 82 lines · 64 tokens per session scan A 2ab03c6ab67f
harness-cicd is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 14d ago), licensed MIT. It adds 64 tokens to every session and 721 once invoked, about $0.0003 per session on Opus 5.5. 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
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
managing-github-actions-secrets
Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.
ci-fixer
CI failures - read error, minimal fix, verify.