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/planejar-fase)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/planejar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/planejar-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/planejar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/planejar-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 | $0.00021 | $0.00884 |
| Opus 5 | $0.00010 | $0.00442 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
planejar-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 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.
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.
What it actually says
Fluxo padrão: Pesquisa (se necessário) → Planejar → Verificar → Concluído
Papel do orquestrador: Analisar argumentos, validar fase, pesquisar domínio (a menos que pulado), invocar planner, verificar com plan-checker, iterar até aprovação ou máximo de iterações, apresentar resultados.
<execution_context> @./.claude/framework/workflows/plan-phase.md @./.claude/framework/references/ui-brand.md </execution_context>
Flags:
--research— Forçar re-pesquisa mesmo que RESEARCH.md exista--skip-research— Pular pesquisa, ir direto para planejamento--gaps— Modo de fechamento de lacunas (lê VERIFICATION.md, pula pesquisa)--skip-verify— Pular loop de verificação--prd <file>— Usar um arquivo PRD/critérios de aceite em vez de discutir-fase. Analisa requisitos em CONTEXT.md automaticamente. Pula discutir-fase completamente.--reviews— Replanejar incorporando feedback de revisão cross-AI do REVIEWS.md (produzido por/revisar)--text— Usar listas numeradas em texto simples em vez de menus TUI (necessário para sessões remotas/rc)
Normalizar entrada da fase no passo 2 antes de qualquer pesquisa de diretório.
<observability_integration> Integração com ODD plan-checker gate (v1.9):
Quando workflow.observability_plan_gate = true (default para fases voltadas ao usuário), o plan-checker invocado neste workflow inclui uma checagem extra:
- Lê
<observability>section do CONTEXT.md (criado por/discutir-faseou/instrumentar-fase) - Verifica que as 4 perguntas pré-PR estão respondidas (consulta skill
observability-driven-development):- Faz o que esperei? → INSTRUMENTATION.md tem
result.successdocumentado? - Compara à versão anterior? →
build_idem todo span planejado? - Usuários estão usando? → identidade (
user.id/tenant_id/customer.tier) presente? - Anomalias emergem? →
error.typeenum +branch_takenplanejados?
- Faz o que esperei? → INSTRUMENTATION.md tem
- Se alguma pergunta ausente: VERIFICATION.md status =
gaps_found, sugerindo invocar/instrumentar-fasepara gerar INSTRUMENTATION.md.
Fases de infraestrutura pura (skip discuss already detectou): pula gate silenciosamente.
Quando há observability gate enabled e gap encontrado: o user pode (a) /instrumentar-fase antes de prosseguir; ou (b) editar manualmente CONTEXT.md <observability> section; ou (c) override via --skip-observability-gate.
REQ: INT-FW-02. </observability_integration>
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 · 68 lines · 21 tokens per session scan A e37e2eec868d
planejar-fase is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 884 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.