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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/commands/luanpdd/kit-mcp/pesquisar-fase)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/pesquisar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/pesquisar-fase/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.
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/pesquisar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/pesquisar-fase.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01518 |
| Opus 5 | $0.00011 | $0.00759 |
| Sonnet 5 | $0.00004 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
pesquisar-fase 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nota: Este é um comando de pesquisa standalone. Para a maioria dos fluxos, use /planejar-fase que integra a pesquisa automaticamente.
Use este comando quando:
- Você quer pesquisar sem planejar ainda
- Você quer re-pesquisar após o planejamento estar completo
- Você precisa investigar antes de decidir se uma fase é viável
Papel do orquestrador: Analisar fase, validar contra o roadmap, verificar pesquisa existente, reunir contexto, invocar agente pesquisador, apresentar resultados.
Por que subagente: Pesquisa consome contexto rapidamente (WebSearch, consultas Context7, verificação de fontes). Contexto fresco de 200k para investigação. Contexto principal fica enxuto para interação com o usuário.
<available_agent_types> Tipos de subagentes framework válidos (use nomes exatos — não use 'general-purpose' como fallback):
- phase-researcher — Pesquisa abordagens técnicas para uma fase </available_agent_types>
Normalizar entrada da fase no passo 1 antes de qualquer busca de diretório.
0. Inicializar Contexto
INIT=$(node "./.claude/framework/bin/tools.cjs" init phase-op "$ARGUMENTS")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
Extrair do JSON de init: phase_dir, phase_number, phase_name, phase_found, commit_docs, has_research, state_path, requirements_path, context_path, research_path.
Resolver modelo do pesquisador:
RESEARCHER_MODEL=$(node "./.claude/framework/bin/tools.cjs" resolve-model phase-researcher --raw)
1. Validar Fase
PHASE_INFO=$(node "./.claude/framework/bin/tools.cjs" roadmap get-phase "${phase_number}")
Se found for false: Erro e sair. Se found for true: Extrair phase_number, phase_name, goal do JSON.
2. Verificar Pesquisa Existente
ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
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.
- 8d ago First seen · 196 lines · 22 tokens per session scan A e524734d6f4e
pesquisar-fase is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 1,518 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.