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 tatagoncalvesof/imperatriz-toolkit --skill gates-imperatrizgit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-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/tatagoncalvesof/imperatriz-toolkit/gates-imperatriz)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/gates-imperatriz"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/gates-imperatriz/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/tatagoncalvesof/imperatriz-toolkit/gates-imperatriz"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/gates-imperatriz.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 | $0.00275 | $0.03286 |
| Opus 5 | $0.00138 | $0.01643 |
| Sonnet 5 | $0.00055 | $0.00657 |
| Haiku 4.5 | $0.00028 | $0.00329 |
Grade A, and why
gates-imperatriz 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gates Imperatriz — Operador do Pilar 2 (Fluxo) da Travessia
Skill que opera as 26 portas (A-Z) da Travessia Imperatriz como um sistema de gates objetivos. Cada porta tem critério mensurável de saída. Cada sintoma tem porta-âncora upstream. Cada ciclo tem cadência fixa. Sem subjetivismo. Sem "acho que tá bom".
Não é a metodologia. É o cobrador da metodologia. A Travessia diz pra onde ir; esta skill valida se já chegou.
Filosofia central
- Porta só fecha com evidência mensurável. "A mentorada acha que está pronta" não fecha gate. Métrica fecha. Artefato fecha. Caso real fecha.
- Sintoma é sintoma, causa é porta. Tráfego caro raramente é problema do tráfego. CPA alto raramente é problema do criativo. Sintoma aparece em K, causa mora em C ou J.
- Pular porta gera dívida composta. Quem fecha B sem ICP claro paga juros em K, L e M. A skill detecta a porta-fonte e devolve a mentorada pra lá.
- Dependência é dura, não suave. E não pode rodar sem C+D. K não pode rodar sem J+H. Skill bloqueia avanço quando upstream falhou.
- Ciclos voltam, mesmo depois de fechados. N é semanal pra sempre. X é trimestral pra sempre. Skill cobra a cadência.
- Diagnóstico é seco. Sem psicologismo, sem "respira fundo". Aponta porta, evidência faltando, ação concreta. Próximo passo.
Quando usar
- Tata revisa carteira de mentoradas e quer saber em que porta cada uma está
- Mentorada acha que terminou uma porta e quer validação objetiva
- Mentorada tem sintoma (CPA alto, reembolso, burnout) e quer saber a causa-porta
- Tata quer mapa de dependências antes de mandar mentorada pra próxima porta
- Time da Tata roda audit trimestral X e precisa do checklist de portas
- Mentorada já completou A-K e quer saber qual ciclo recorrente está vencido
- Antes de chamar
/tatou-2.0pra construir próximo passo — esta skill define qual é o próximo passo
Quando NÃO usar
- Mentorada precisa aprender o que é uma porta (chama Travessia direto, não a skill)
- Tata quer escrever copy, criar oferta, montar funil (chama skill específica)
- Mentorada quer coaching emocional sobre estar travada (não é o escopo)
- Diagnóstico inicial de quem nunca rodou Travessia (chama
/dossie-mentoradaantes)
What ships with it
6 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.
- 11d ago First seen · 312 lines · 275 tokens per session scan A 31b7a0d93cd7
gates-imperatriz is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 275 tokens to every session and 3,286 once invoked, about $0.0014 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
fp-brief
First-principles briefing from technical documents. Use when: understanding why decisions were made, onboarding to feature reasoning, reviewing decision chains, explaining doc from first principles. Not for: PM/CTO summary (use project-brief), pre-doc analysis (use feasibility-study), code explanation (use…
codex-explain
Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.
sharingan
Replicate knowledge from any source as sd0x-dev-flow skill definition. Use when: copying skills from repos, adapting patterns from articles/papers/code, converting knowledge to skill format. Not for: research without skill output (use deep-research), creating skills from scratch (use skill-creator), project onboarding…
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
explaining-codebases
Use when creating an interactive explainer about a codebase, repository, or source files. Handles onboarding overviews, architecture maps, and deep-dives on real implementation paths. Trigger phrases include "explain this codebase", "interactive guide to this repo", "walk through how X works in the code", or…
openehr-assistant
This skill should be used when a conversation touches openEHR outside a task owned by a dedicated skill — e.g. "what is an archetype?", "how do openEHR templates work?", "which composition category fits this data?", "find me a guide on X", "where do I start with openEHR modeling?" — or names openEHR concepts (ADL…