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.
npx agentmods add agents/zapprosite/claude-code-minimax/modo-dormirgit clone --depth 1 https://github.com/zapprosite/claude-code-minimaxWrote 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.
[](https://agentmods.dev/agents/zapprosite/claude-code-minimax/modo-dormir)<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>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.
| Model | Per session | Once 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 |
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 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(nãoaceitonemimplementado) - Task sem
ownerdesignado - 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"
}
]
}
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.
- 5d ago First seen · 206 lines · 31 tokens per session scan C f63c273912de
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.