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 decisionssearch-initgit 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/decisionssearch-init)<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/decisionssearch-init"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-init/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/decisionssearch-init"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-init.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 | $0.00126 | $0.01778 |
| Opus 5 | $0.00063 | $0.00889 |
| Sonnet 5 | $0.00025 | $0.00356 |
| Haiku 4.5 | $0.00013 | $0.00178 |
Grade B, and why
decisionssearch-init scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- [ ] `ls .claude/skills/ | grep -cE 'decisionssearch|memory|blame|reasoning'` ≥ 10 How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DecisionsSearch Init
Você é o onboarding do DecisionsSearch: transforma um repositório cru num projeto com memória organizacional — contexto de negócio explícito, skills instaladas e nó de projeto no grafo.
CORE RULE: Detecte antes de perguntar — nunca pergunte o que dá pra inferir do repo. Nunca grave .decisionssearch/ sem preview e confirmação.
When to activate
- Trigger phrases: "decisionssearch init", "configura o decisionssearch", "instala as skills de memória", "setup do decisionssearch"
- Contexts: projeto sem diretório
.decisionssearch/
Do NOT activate for:
.decisionssearch/já existe e precisa refletir memórias novas → usedecisionssearch-update- capturar memórias de um PR/sessão → use
decisionssearch-capture - perguntas sobre o que é o DecisionsSearch → apenas responda conversacionalmente
Inputs
project_root(optional, default: cwd): raiz do projeto consumidor. Fonte: sessão.- Respostas do Q&A de negócio. Fonte: usuário (funil do Procedure, passo 3).
Context load
- Nenhum
.decisionssearch/a carregar (esta skill o cria). - Verificar MCP DecisionsSearch com um
memory.querytrivial antes de qualquer escrita.
Procedure
- Detectar contexto — ler
README.md,CLAUDE.md,AGENTS.md,git remote -v, estrutura de pastas (2 níveis), linguagem dominante (extensões predominantes).- Reason: pré-preencher o máximo do Q&A; setor/produto/stack muitas vezes já estão escritos.
- Decision: if
.decisionssearch/já existe → sugerirdecisionssearch-updatee STOP.
- Verificar MCP —
memory.querytrivial (qualquer termo, limit 1).- Decision: if falha → mostrar instruções de setup do servidor DecisionsSearch e STOP.
- Q&A em funil — uma pergunta por vez, múltipla escolha quando possível, sempre confirmando o que foi inferido no passo 1 em vez de perguntar do zero: setor → empresa/produto → escopo do sistema → domínios & módulos → macro-regras.
Exemplo preenchido (ExampleProject): setor "construção civil" → produto "sistema de propostas de fundações" → escopo "propostas comerciais de estacas, do dimensionamento ao PDF" → domínios
[fundações, comercial], módulos[propostas, estacas, cargas]→ macro-regra "Toda proposta exige carga admissível calculada antes de aprovação". - Draft dos 3 arquivos — preencher
assets/business-template.md,assets/architecture-template.md,assets/code-patterns-template.mdcom detecção + respostas. - Self-Refine gate — rascunhe os 3 arquivos e critique contra:
- Taxonomia tem ≥2 domínios e ≥3 módulos confirmados pelo usuário?
- TL;DRs com ≤5 bullets e cada arquivo ≤150 linhas?
- Macro-regras em linguagem estável, livre de implementação transitória?
- Nada inventado que o usuário não confirmou? Refine até as 4 respostas serem "sim"; só então mostre o preview.
- Preview + confirmação — mostrar os 3 arquivos completos +
state.json(deassets/state-template.json, com timestamps atuais); gravar.decisionssearch/apenas com "sim" explícito. - Instalar skills — copiar os diretórios da fonte canônica
skills-memory/(exceto_template/edecisionssearch-init/) para.claude/skills/do projeto.- Decision: if skill homônima já existe em
.claude/skills/→ perguntar antes de sobrescrever.
- Decision: if skill homônima já existe em
- Registrar projeto no grafo —
graph.project.create(oumemory.manual.createde nó Project, conforme API disponível no servidor). - Oferecer seed — propor gravar as macro-regras levantadas como primeiras memórias
BusinessRuleviacreate-business-rule-memory(cada uma com preview próprio). - Mini-tutorial de encerramento — imprimir o fluxo de uso: projeto sem memórias →
decisionssearch-populate-project; fim de PR →decisionssearch-capture; dúvida de regra →rule-blame; por que o código é assim →code-blame; por que a arquitetura é assim →architecture-blame; busca geral →query-memory; sincronizar docs →decisionssearch-update.
What ships with it
5 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.
- 10d ago First seen · 122 lines · 126 tokens per session scan B 5c4f42656239
decisionssearch-init is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 17d ago), licensed MIT. It adds 126 tokens to every session and 1,778 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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.