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 Renzo-Tognella/DecisionsSearch --skill capture-reasoninggit clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearchWrote 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/renzo-tognella/decisionssearch/capture-reasoning)<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/capture-reasoning"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/capture-reasoning/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/renzo-tognella/decisionssearch/capture-reasoning"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/capture-reasoning.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 | $0.00075 | $0.01991 |
| Opus 5 | $0.00037 | $0.00996 |
| Sonnet 5 | $0.00015 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
capture-reasoning 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 10d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Reasoning
Você é o analisador de reasoning da sessão: preserva o PROCESSO de decisão de uma task — plano, tentativas, porquês de percurso — para que uma task parecida no futuro recupere "como resolvemos da última vez".
CORE RULE: Capture o PROCESSO (abordagem, tentativas, porquês de percurso), não o artefato. Antes de olhar a sessão, peça a escolha do usuário. Nunca persista sem preview e confirmação.
When to activate
- Trigger phrases: "captura o reasoning dessa task", "salva o plano e as decisões dessa sessão", "registra como resolvemos esse card"
- Contexts: fechamento de card/task com pedido explícito de registrar o processo
Do NOT activate for:
- decisão durável com alternativas (tecnologia, estrutura) → use
create-architectural-decision-memory - buscar reasoning de tasks passadas ("já fizemos algo assim?") → use
query-memory - criar memória do PR em si → use
create-pr-memory - backfill histórico ou
decisionssearch-populate-project→ não use esta skill - captura em lote de fim de PR → não use esta skill automaticamente
Inputs
mode: semprestandalone; esta skill não participa de backfill nem de captura em lote.session_review(required): escolha explícita do usuário entreentire_current_sessionebounded_summary.bounded_summary(required se o usuário não autorizar a sessão inteira): resumo fornecido pelo usuário com objetivo, abordagem, alternativas/limites e resultado.related_memory_ids(optional): ids de memórias já criadas na mesma captura (ex.: a PRMemory, uma AD) para vincular ao episódio no momento da criação.
Context load
- Carregar
.decisionssearch/business.md(taxonomia para contextualizar objetivo/tags). - Se o arquivo não existir → sugerir
decisionssearch-inite STOP. - Verificar MCP DecisionsSearch com um
memory.querytrivial antes de qualquer escrita. - Antes de ler, resumir ou usar turnos anteriores, perguntar exatamente: “Para preparar esta memória avulsa, quer que eu considere toda a sessão atual ou apenas as fontes que você indicar?”
- Sessão inteira: varrer somente a sessão atual disponível e usar apenas fatos que sustentem o episódio.
- Apenas fontes indicadas: não varrer turnos anteriores; pedir um
bounded_summaryse ele ainda não foi dado. - Esta escolha controla o contexto de análise, não substitui o preview nem a confirmação de persistência.
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.
- 10d ago First seen · 117 lines · 75 tokens per session scan A a61bbb09d3dc
capture-reasoning is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 17d ago), licensed MIT. It adds 75 tokens to every session and 1,991 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.