create-pr-memory

create-pr-memory is a skill for Claude Code, Codex from Renzo-Tognella/DecisionsSearch. It costs 112 tokens per session (3,035 once invoked), scanned A, original, MIT.

A workflow for turning a pull request into a durable project-memory record. It records the PR’s purpose, complete list of changed files, effects, affected people, rules, and triggered actions based on Git and the PR history.

In plain words
What is it for?
Saving an open or merged PR as searchable operational history in DecisionsSearch.
Why use it?
It keeps the practical meaning of a change available after the original diff is no longer open.

Skill for Claude CodeCodex

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

Good fit Saving an open or merged PR as searchable operational history in DecisionsSearch.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/create-pr-memory.svg)](https://agentmods.dev/skills/renzo-tognella/decisionssearch/create-pr-memory)
Your own site
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/create-pr-memory"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/create-pr-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,035 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 $0.00112 $0.03035
Opus 5 $0.00056 $0.01517
Sonnet 5 $0.00022 $0.00607
Haiku 4.5 $0.00011 $0.00303

Measured 7d ago against content hash 31475bb44243, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

create-pr-memory 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 7d 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/create-pr-memory/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PR Memory

Você cria uma memória operacional de Git Blame para um PR: o que mudou, qual era o objetivo, quais arquivos foram alterados, quem é afetado, que regras aparecem e quais ações o comportamento dispara. A memória deve continuar útil quando o diff já não estiver aberto.

CORE RULE: Leia o PR, o diff e o histórico real (gh + Git) antes de sintetizar. changed_files é sempre a lista completa de arquivos alterados. Nunca persista sem preview e confirmação explícita.

When to activate

  • Trigger phrases: "cria a memória desse PR", "salva o PR #N na memória", "registra esse PR no decisionssearch"
  • Contexts: PR aberto ou mergeado que deve virar memória; passo sempre-roda da decisionssearch-capture

Do NOT activate for:

  • regra de domínio sem PR específico → use create-business-rule-memory
  • decisão de design/arquitetura → use create-architectural-decision-memory
  • padrão reutilizável explicitamente evidenciado → use create-code-pattern-memory
  • consultar PRs existentes → use query-memory

Inputs

  • pr (required): número, URL ou branch do PR. Fonte: usuário ou sessão.
  • mode (optional, default: standalone): standalone (coleta própria via gh e Git) | orchestrated (recebe digest pronto da decisionssearch-capture e ainda valida a evidência antes de escrever).
  • digest (required se mode: orchestrated): digest com o PR e as evidências já coletadas.
  • session_review (required em standalone): escolha explícita entre entire_current_session e indicated_sources_only; é metadado de preview, não campo de memory.pr.create.

Context load

  • Carregar .decisionssearch/business.md; a taxonomia é a fonte oficial para areas/modules.
  • Se o arquivo não existir → sugerir decisionssearch-init e STOP.
  • Verificar MCP DecisionsSearch com um memory.query trivial antes de qualquer escrita.
  • Em standalone, antes de ler ou resumir 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: usar a sessão atual apenas como evidência complementar de objetivo, contexto ou lacuna; PR, diff e Git continuam sendo a fonte primária.
    • Apenas fontes indicadas: não usar turnos anteriores; trabalhar somente com PR, diff, Git e fontes apontadas pelo usuário.
    • Em orchestrated, não perguntar nem varrer a sessão: usar somente o digest/evidência fornecido pelo orquestrador.
    • A escolha não substitui o preview nem a confirmação de persistência.

Read the full file on GitHub · 187 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. 7d ago First seen · 187 lines · 112 tokens per session scan A 31475bb44243

Subscribe to this mod's changes

create-pr-memory is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 14d ago), licensed MIT. It adds 112 tokens to every session and 3,035 once invoked, about $0.0006 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.