modo-dormir

modo-dormir is an agent for Claude Code from zapprosite/claude-code-minimax. It costs 31 tokens per session (1,454 once invoked), scanned C, original, MIT.

An agent that scans a repository for work items in formats such as task lists, product requirements, architecture decisions, slices, issues, and Turbo configuration.

In plain words
What is it for?
Use it to generate pipeline.json, unify task details such as status and priority, create smoke tests, and produce curl scripts.
Why use it?
It consolidates scattered task sources into one pipeline and identifies tasks that need human approval.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

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/zapprosite/claude-code-minimax/modo-dormir
Clone the repo
git clone --depth 1 https://github.com/zapprosite/claude-code-minimax

Made for: Claude Code.

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 modo-dormir

README.md
[![agentmods](https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/modo-dormir.svg)](https://agentmods.dev/agents/zapprosite/claude-code-minimax/modo-dormir)
Your own site
<a href="https://agentmods.dev/agents/zapprosite/claude-code-minimax/modo-dormir"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/modo-dormir.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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 5.1 $0.00031 $0.01454
Opus 5 $0.00015 $0.00727
Sonnet 5 $0.00006 $0.00291
Haiku 4.5 $0.00003 $0.00145

Measured 5d ago against content hash f63c273912de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

modo-dormir scanned grade C with 2 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Bash(rm -rf /srv*)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Agent modo dormir — escaneia repo por tasks em múltiplos formatos, gera pipeline.json, cria smoke tests e curl scripts
.claude/agents/modo-dormir.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modo Dormir Agent

Executa scan completo de repositório enquanto você dorme. Quando acordado, relatório pronto com pipeline e testes.

Fluxo de Execução

Fase 1: Detectar Formatos

Escaneia o repo por todos os formatos de task suportados:

Formato Padrão Schema
TASKMASTER **/TASKMASTER*.json, **/taskmaster*.json { tasks: [{ id, title, status, owner }] }
PRD **/prd.md, **/PRD.md Markdown sections ## Funcionalidade, ## Critérios
ADR **/docs/ADR/*.md, **/docs/adr/*.md MADR ou compact ADR format
SLICE **/*.slice.md, git branches feature/slice-* Slices numerados
TODO **/TODO.md, **/task*.md Lista markdown
ISSUE GitHub via MCP { number, title, labels, state }
TURBO **/turbo.json { tasks: { name, dependsOn } }

Fase 2: Parsear Tasks

Extrai tasks de cada formato e consolida em lista unificada:

{
  "tasks": [
    {
      "id": "CRM-001",
      "title": "Implementar autenticação JWT",
      "source": "TASKMASTER",
      "status": "todo",
      "owner": null,
      "priority": "high",
      "human_gate": false
    }
  ]
}

Fase 3: Detectar Human Gates

Identifica pontos que requerem aprovação humana:

  • Label/keyword: needs-approval, blocked, PM-review, security, infra
  • PRD com seção ## Aprovação
  • ADR status: proposto (não aceito nem implementado)
  • Task sem owner designado
  • Task com status: blocked

Fase 4: Gerar Pipeline

Gera pipeline.json com fases e gates:

{
  "name": "repo-scan-pipeline",
  "repo": "/path/to/repo",
  "generated": "2026-04-05T03:00:00Z",
  "phases": [
    {
      "name": "fase1_core",
      "tasks": ["CRM-001", "CRM-002"],
      "agent": "builder",
      "human_gate": false
    },
    {
      "name": "fase2_approval",
      "tasks": ["CRM-003"],
      "agent": "auditor",
      "human_gate": true,
      "gate_reason": "needs-PM-review",
      "approver": "human:PM"
    }
  ]
}

Read the full file on GitHub · 206 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. 5d ago First seen · 206 lines · 31 tokens per session scan C f63c273912de

Subscribe to this mod's changes

modo-dormir is an agent published in the GitHub repository zapprosite/claude-code-minimax (2 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,454 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.