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 juliano-ceconi/okam --skill wiki-de-conhecimentogit clone --depth 1 https://github.com/juliano-ceconi/okamWrote 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/juliano-ceconi/okam/wiki-de-conhecimento)<a href="https://agentmods.dev/skills/juliano-ceconi/okam/wiki-de-conhecimento"><img src="https://agentmods.dev/badge/skills/juliano-ceconi/okam/wiki-de-conhecimento/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/juliano-ceconi/okam/wiki-de-conhecimento"><img src="https://agentmods.dev/badge/skills/juliano-ceconi/okam/wiki-de-conhecimento.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 | $0.00024 | $0.00419 |
| Opus 5 | $0.00012 | $0.00210 |
| Sonnet 5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
wiki-de-conhecimento 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.
What it actually says
📚 Wiki de Conhecimento
Esta skill define as operações para manter o sistema de conhecimento persistente do workspace.
Estrutura do Wiki
- Localização:
./knowledge/ - raw-sources/: Fontes brutas, imutáveis (PDFs, Markdown clippado, logs).
- wiki/: Páginas de síntese geradas por IA seguindo o formato OKF.
Operações Principais
1. Ingest (Ingestão)
Sempre que uma nova fonte for adicionada a raw-sources/:
- Leia o conteúdo da fonte.
- Identifique os temas, entidades e conceitos principais.
- Compare com o conhecimento já existente no
wiki/. - Crie ou Atualize páginas no
wiki/. - Atualize o
index.mde olog.md.
2. Query (Consulta)
Ao responder perguntas sobre o conhecimento acumulado:
- Comece consultando o
index.mddo Wiki. - Siga os links para as páginas de síntese relevantes.
- Se houver lacunas, consulte as
raw-sources/. - Se a descoberta for valiosa, protocole a resposta como uma nova página no Wiki.
3. Lint (Auditoria)
Periodicamente, revise o Wiki em busca de:
- Contradições entre documentos novos e antigos.
- Páginas órfãs (sem links de entrada).
- Conceitos mencionados mas sem página própria.
Padrões de Escrita
- Use links
[[Nome da Página]]para referências cruzadas. - Adicione frontmatter YAML no formato OKF (title, description, type, resource, timestamp, tags, parent).
- Valide antes de commitar:
python ./knowledge/scripts/okf_manager.py --validate.
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 · 50 lines · 24 tokens per session scan A 6565077d9cbe
wiki-de-conhecimento is a skill published in the GitHub repository juliano-ceconi/okam (2 stars, last pushed 25d ago), licensed MIT. It adds 24 tokens to every session and 419 once invoked, about $0.0001 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
R-cleanup-context
Audit and clean CLAUDE.md, memory, skills, and rules — resolve every finding (fix/promote/relocate/delete), track recurrences, target bloat=0. Triggers: "cleanup context" | "context audit" | "clean memory" | "drain memory" | "prune memory" | "audit memory" | "consolidate rules" | "spa day" | "memory audit".
memoria
Memoria Persistente Tienes acceso a una base de datos de memoria persistente.
agentmemory-agents
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…