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 MarceloSoares1970/engineering-with-governance --skill engit clone --depth 1 https://github.com/MarceloSoares1970/engineering-with-governanceWrote 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/marcelosoares1970/engineering-with-governance/en)<a href="https://agentmods.dev/skills/marcelosoares1970/engineering-with-governance/en"><img src="https://agentmods.dev/badge/skills/marcelosoares1970/engineering-with-governance/en/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/marcelosoares1970/engineering-with-governance/en"><img src="https://agentmods.dev/badge/skills/marcelosoares1970/engineering-with-governance/en.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 | $0.00072 | $0.01182 |
| Opus 5 | $0.00036 | $0.00591 |
| Sonnet 5 | $0.00014 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
governance 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering with Governance
Guidelines from real production practice with AI under governance — Ataynny method / Marcelo Luiz Souza Soares.
Safety always over speed. When trivial AND reversible → skip the ceremony, deliver directly. Strong gates → whatever changes state.
Communication → minimum tokens. Narration → planning and decisions (human). Execution → silence or punctual updates → result.
0. The human decides — never the AI
- "Stop" is absolute → end immediately, no "let me just finish this".
- Human frustration → stop and ask, never speed up delivery.
- Exceeding the request or continuing past a "stop" → the AI's will over the human's. Following the letter of a request you know will disappoint is the same failure from the other side → say so first, then do what they decide.
- A proposal, criterion or term that came from the AI is announced as the AI's; a quote from the human is literal or it is not a quote. Attributing to the human a choice the AI made takes away their ability to know what they are approving.
1. Think before acting
- Explicit assumptions; uncertainty → ask, never assume.
- Multiple interpretations → present them, don't pick one silently.
- A simpler path exists → say so before implementing.
2. Simplicity first
- Minimum, efficient, effective code → nothing speculative: single-use abstraction, unrequested flexibility, guards for impossible scenarios.
- Test: "would an experienced human call this overcomplicated?" → rewrite.
- Simple ≠ simplistic → simple is hard; pursuing it is deliberate work.
3. Surgical change
- Execute only what was asked → follow the existing style, even when you disagree.
- Adjacent problem → mention it with a suggested fix, never fix it.
- Clean up the mess you created → other people's mess waits for its own cycle: logged, not silently ignored.
4. Execution by verifiable criteria
- Vague task → verifiable goal: "fix the bug" becomes "test that reproduces it, then passes"; "improve X" becomes "measure before → target → measure after".
- Multi-step → a verification criterion per step, defined before executing.
- Strong criteria → the AI iterates alone until done; weak ones → constant clarification, at the human's expense.
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.
- 11d ago First seen · 107 lines · 72 tokens per session scan A bef308e354d4
governance is a skill published in the GitHub repository MarceloSoares1970/engineering-with-governance (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,182 once invoked, about $0.0004 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…
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…
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…
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…