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 imperio-memoriagit 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/imperio-memoria)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/imperio-memoria"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-memoria/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/imperio-memoria"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-memoria.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 | $0.00000 | $0.05871 |
| Opus 5 | $0.00000 | $0.02936 |
| Sonnet 5 | $0.00000 | $0.01174 |
| Haiku 4.5 | $0.00000 | $0.00587 |
Grade A, and why
imperio-memoria 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPERIO MEMORIA — Sistema de Memoria para Agentes IA
Skill que projeta e implementa o sistema de memoria de agentes IA — gestao de estado, contexto compartilhado e decisoes de RAG. Aplica 3 frameworks da "Apostila Imperio IA Agentes" by Tata Goncalves.
ACTIVATION
Trigger this skill when:
- User mentions "memoria de agentes", "estado dos agentes", "state management agentes"
- User asks "como meus agentes lembram?", "agentes compartilham info?", "preciso de RAG?"
- User mentions "cerebro", "diario", "bussola" in context of AI agents
- User says
/imperio-memoria - User asks about shared context between agents, agent state, or RAG decisions
FRAMEWORKS
This skill applies 3 proprietary frameworks from the Apostila Imperio IA Agentes:
1. CEREBRO (Gestao de Estado)
Every agent that runs more than once NEEDS a state file. Without it: actions duplicate, progress is lost, messages repeat, behavior becomes inconsistent.
2. DIARIO (Memoria Compartilhada)
When multiple agents operate in the same business, they MUST read from ONE source of truth. Without it: one agent promises a discount, another doesn't know about it.
3. BUSSOLA (Decisao RAG)
Not every system needs RAG. The BUSSOLA framework decides: simple files vs vector database, based on document count, update frequency, access patterns, and prompt size.
EXECUTION FLOW
Execute steps 1-5 in order. Each step has a clear deliverable. NEVER skip steps. ALWAYS collect information before generating.
STEP 1: Entender o Ecossistema de Agentes
Objetivo: Mapear todos os agentes, suas funcoes e interacoes.
Perguntar (uma pergunta por vez, aguardar resposta):
- "Quantos agentes voce tem (ou vai ter) no seu negocio? Me lista eles com o que cada um faz."
- "Esses agentes precisam compartilhar informacao entre si? Sobre o que? (ex: dados de clientes, decisoes comerciais, historico de conversas)"
- "Voce tem agentes que rodam mais de 1 vez — tipo cron diario, reativo a evento? Quais?"
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 · 579 lines · 0 tokens per session scan A 1b15336dd206
imperio-memoria is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,871 tokens. 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
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.
pm-engine
Interface with the PM-ENGINE-MEMORY file — the operator's accumulated PM tacit knowledge database. Enables agents to reference, search, and apply TK (Tacit Knowledge) entries, and supports TK extraction from experience (--mode extract), TK querying and referencing (--mode query), and TK-to-instruction conversion…
maintaining-project-context
Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed, determines affected contracts and documentation, and coordinates updates.
memory-arch
Design an agent memory system — working memory, episodic memory, semantic memory, and procedural memory. Use when building agents that need to remember context across sessions, learn from interactions, or maintain persistent knowledge. Covers storage strategy, retrieval patterns, and context management.
vibe-session-context-flush
Performs smart context summarization when the context window is approaching capacity. Identifies what to keep, what to summarize, and creates a compact resume state.
vibe-debugging-journal
Records resolved bugs in a persistent journal — symptom, root cause, difficulty, fix, prevention. Organized by category for future reference.