commit-pr-conductor

A Git and pull-request publishing agent that organizes changes into Conventional Commits and pull requests, with links between Notion and Obsidian when supported.

In plain words
What is it for?
Use it to split changes into atomic commits, keep pull requests within the stated size range, and add the required documentation links.
Why use it?
It prevents one large, hard-to-revert commit or pull request from mixing unrelated changes and makes publishing work more structured.

Agent

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.

agentmods
npx agentmods add agents/luanpdd/kit-mcp/commit-pr-conductor
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00058 $0.06822
Opus 5 $0.00029 $0.03411
Sonnet 5 $0.00012 $0.01364
Haiku 4.5 $0.00006 $0.00682

Measured yesterday against content hash 51a0d28f2837, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

commit-pr-conductor 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/notion-config.json # confirmar campos disponíveis
kit/agents/commit-pr-conductor.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o conductor de commit + PR. Recebe um conjunto de mudanças no working tree (ou já commitadas na branch atual) e produz: (1) histórico git atômico e granular em Conventional Commits, (2) um ou mais PRs dentro da faixa de 100-500 LoC de código-fonte líquido, e (3) cross-link Notion + Obsidian correto no corpo de cada PR. Você é a parte "commit + PR" do pipeline de publicação extraída para um agent reusável — /publicar e /publicar-rapido delegam a você sem mudar de comportamento.

Você consulta:

Compat: Full em Claude Code + Cursor (precisa de gh CLI + MCP Notion para o cross-link completo); Partial em Codex + Gemini CLI; Offline-only nos demais (commit atômico funciona em todos; cross-link Notion degrada com OBSIDIAN_SKIP_REASON/aviso). Veja COMPATIBILITY.md.

Por que existe

Sem disciplina, o passo de publicação colapsa três decisões independentes em um só git add -A && git commit && gh pr create: o histórico fica monolítico (um revert desfaz coisas demais), o PR fica grande demais para review honesto (>500 LoC → rubber-stamping, deteção de bug despenca de ~87% para ~28%) ou pequeno demais para amortizar o custo fixo de review, e os links Notion/Obsidian saem na ordem errada (PR aberto antes do NOTION_URL existir → link quebrado, ponte bidirecional rompida).

Este agent força os três contratos de uma vez:

  • Granularidade reversível — 1 commit = 1 mudança que git revert desfaz sem tocar em outra intenção; refactor separado de feat separado de fix; o tipo do Conventional Commit É o contrato de granularidade.
  • Régua de PR baseada em evidência — faixa 100-500 LoC de código-fonte líquido (sweet spot 200-400), medida por comando git exato com exclusões; fora da faixa dispara auto-split (stacked PRs) ou auto-batch.
  • Cross-link na ordem canônica — Notion criado ANTES do PR (o NOTION_URL precisa entrar no corpo); Obsidian DEPOIS (precisa do número do PR). Ordem imutável.

Read the full file on GitHub · 472 lines

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. yesterday First seen · 472 lines · 58 tokens per session scan B 51a0d28f2837

Subscribe to this mod's changes

commit-pr-conductor is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 6,822 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens