decisionssearch-populate-project

decisionssearch-populate-project is a skill for Claude Code, Codex from Renzo-Tognella/DecisionsSearch. It costs 77 tokens per session (3,346 once invoked), scanned A, original, MIT.

A workflow for filling an existing project’s memory from user-approved files, documents, Git commits, and pull requests. It creates and connects different kinds of memories while checking for duplicates and preserving evidence.

In plain words
What is it for?
Onboarding an older project by importing its documentation, code history, commits, and PRs into organised business, architecture, and code-pattern memories.
Why use it?
It makes historical project knowledge searchable without reading outside the sources the user named or turning unsupported details into facts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Onboarding an older project by importing its documentation, code history, commits, and PRs into organised business, architecture, and code-pattern memories.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/decisionssearch-populate-project"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/decisionssearch-populate-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,346 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 $0.00077 $0.03346
Opus 5 $0.00039 $0.01673
Sonnet 5 $0.00015 $0.00669
Haiku 4.5 $0.00008 $0.00335

Measured 11d ago against content hash ca5d78731fce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

decisionssearch-populate-project 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.

skills-memory/decisionssearch-populate-project/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DecisionsSearch Populate Project

Você é a orquestradora de onboarding histórico de um projeto. Seu trabalho é transformar fontes autorizadas pelo usuário — documentação, arquivos, commits e PRs — em um conjunto idempotente de memórias navegáveis, preservando evidência, separando classes e mantendo os vínculos verificáveis.

CORE RULE: Nunca rastreie fora do escopo indicado nem persista uma memória sem evidência, verificação de duplicata e preview consolidado aprovado. Não assuma qual repositório é canônico, não trate clone/worktree como projeto novo, nunca leia ou pergunte sobre a sessão atual e nunca crie reasoning no backfill.

Contrato de evidência e prosa

  • Arquivos e documentos são fontes de fatos; o conteúdo deve ser citado como evidência concreta, não transformado automaticamente em memória.
  • PRMemory usa o PR, diff e histórico Git como fonte primária e preserva a lista completa de changed_files, objetivo, efeito e referências do PR.
  • BusinessRule é uma verdade de domínio em prosa, independente da implementação. ArchitecturalDecision exige escolha, rationale e ao menos uma alternativa rejeitada. CodePattern exige padronização explícita ou repetição verificável.
  • Backfill não pergunta se a sessão atual pode ser lida, não a varre e nunca chama capture-reasoning, mesmo que o agente tenha contexto disponível. Não se fabrica o processo da task. FeatureDescription continua sendo narrativa derivada dentro de PRMemory, não um nó separado.
  • Relações só são criadas depois dos nós existirem. Use a API de PR para IMPLEMENTS, EVIDENCES e MODIFIES; use relações entre memórias apenas quando a evidência sustentar REFINES, DEPENDS_ON, EVOLVES_FROM ou outra relação mais específica.

When to activate

  • Trigger phrases: "popula este projeto", "importa as memórias deste repositório", "cria memórias a partir destes arquivos e PRs", "faz o onboarding histórico do projeto"
  • Contexts: projeto já existente com zero ou poucas memórias; usuário fornece uma raiz de projeto, arquivos de referência, commits, PRs ou um seletor explicitamente limitado de PRs mergeados.

Read the full file on GitHub · 285 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. 11d ago First seen · 285 lines · 77 tokens per session scan A ca5d78731fce

Subscribe to this mod's changes

decisionssearch-populate-project is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 18d ago), licensed MIT. It adds 77 tokens to every session and 3,346 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.