decisionssearch-capture

decisionssearch-capture is a skill for Claude Code, Codex from Renzo-Tognella/DecisionsSearch. It costs 91 tokens per session (1,873 once invoked), scanned A, original, MIT.

A workflow for recording the useful knowledge from a pull request (a proposed code change) in a searchable project memory. It reviews the PR, code differences, and approved sources, then links the resulting records.

In plain words
What is it for?
Closing a finished PR by recording its changes, related business rules, architecture decisions, coding patterns, and links between them.
Why use it?
It avoids repeating several separate memory-capture steps and keeps capture limited to evidence the user has approved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Closing a finished PR by recording its changes, related business rules, architecture decisions, coding patterns, and links between them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/renzo-tognella/decisionssearch/decisionssearch-capture
Install

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.

Any agent
npx skills add Renzo-Tognella/DecisionsSearch --skill decisionssearch-capture
Clone the repo
git clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearch

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for decisionssearch-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-capture/github.svg)](https://agentmods.dev/skills/renzo-tognella/decisionssearch/decisionssearch-capture)
Your own site
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/decisionssearch-capture"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-capture/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.

agentmods 80×15 button for decisionssearch-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/decisionssearch-capture"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.01873
Opus 5 $0.00046 $0.00937
Sonnet 5 $0.00018 $0.00375
Haiku 4.5 $0.00009 $0.00187

Measured 10d ago against content hash a20d1dc13d51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

decisionssearch-capture 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.

skills-memory/decisionssearch-capture/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DecisionsSearch Capture

Você é a orquestradora de fim-de-PR: um sweep de PR/diff, uma triagem, um preview consolidado — e o grafo ganha PR, regras, decisões, padrões e links de uma vez, sem seis confirmações sequenciais.

CORE RULE: Um sweep de fontes do PR, uma triagem confirmada, um preview consolidado, links por último. Nunca leia a sessão inteira, nunca crie Episode automaticamente e nunca rode skill filha sem a triagem aprovada.

When to activate

  • Trigger phrases: "decisionssearch capture", "fecha o PR capturando as memórias", "popula a memória desse PR"
  • Contexts: PR finalizado (aberto pra merge ou mergeado) ao fim de uma sessão de trabalho

Do NOT activate for:

  • captura avulsa de uma classe só ("registra essa regra") → use a skill create-* específica
  • projeto sem .decisionssearch/ → use decisionssearch-init
  • sincronizar os documentos com o grafo → use decisionssearch-update

Inputs

  • pr (optional, default: PR do branch atual via gh pr view): número ou URL do PR.
  • Aprovações do usuário: triagem (passo 4) e preview consolidado (passo 6).

Context load

  • Carregar os 3 arquivos .decisionssearch/ (business, architecture, code-patterns).
  • Se .decisionssearch/ não existir → sugerir decisionssearch-init e STOP.
  • Verificar MCP DecisionsSearch com um memory.query trivial antes de qualquer escrita.

Procedure

  1. Pré-condições.decisionssearch/ existe; MCP responde; PR identificado (gh pr view do branch atual ou o número dado).
    • Decision: if qualquer uma falha → STOP com a instrução correspondente (init / setup MCP / informar o PR).
  2. Sweep único → digest do PR — coletar numa passada: diff do PR (gh pr view --json title,number,url,state,author,files,createdAt,mergedAt,headRefName,body + gh pr diff) e fontes explicitamente apontadas pelo usuário. Não ler plano, turnos, alternativas ou correções da sessão atual. Formato:
    digest:
      pr: {number, title, url, files, dates, authors}
      documented_decisions: [{choice, alternatives: [{option, why_rejected}], justification}]
      rules_touched: [candidatas a BusinessRule]
      patterns_introduced: [candidatas a CodePattern]
      gaps: [contexto não evidenciado no PR ou nas fontes indicadas]
    
    • Reason: captura em lote não deve presumir autorização para analisar toda a sessão. Processo/raciocínio só é registrado por capture-reasoning avulsa, após escolha explícita do usuário.
  3. Carregar contexto — os 3 arquivos .decisionssearch/ (taxonomia, decisões vigentes, padrões vigentes) para as triagens do passo 4.
  4. Triagem — aplicar a tabela e apresentar o resultado ANTES de rodar qualquer condicional:

Read the full file on GitHub · 121 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 121 lines · 91 tokens per session scan A a20d1dc13d51

Subscribe to this mod's changes

decisionssearch-capture is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 17d ago), licensed MIT. It adds 91 tokens to every session and 1,873 once invoked, about $0.0005 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.