Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luanpdd/kit-mcpnpx agentmods add commands/luanpdd/kit-mcp/mapear-codebase-workflowWrote 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/mapear-codebase-workflow)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/mapear-codebase-workflow"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/mapear-codebase-workflow.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 | $0.00052 | $0.01319 |
| Opus 5 | $0.00026 | $0.00660 |
| Sonnet 5 | $0.00010 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
mapear-codebase-workflow 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 4d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mapear-codebase-workflow
PoC — Dynamic Workflows (Opus 4.8+). Mesma intenção do
/mapear-codebasemas executa viaWorkflow(): 4 mappers paralelos (1 por área de foco do agentcodebase-mapper) + synthesizer final que verifica os 7 documentos, recupera falha parcial via highlights e roda secret scan.
Use este comando para comparar wall-clock e qualidade dos documentos contra a versão tradicional orquestrada em prosa.
Por que existe (PoC):
- A versão tradicional orquestra 4
Task()em prosa — sem schema de retorno, sem recuperação de falha parcial, sem verificação consolidada. - Esta versão tem 1 contexto por área de foco (mapper pequeno, foco preservado) + synthesizer que verifica os 7 docs no disco, reescreve docs degradados a partir dos highlights e roda o secret scan antes de qualquer commit.
- Mesmos templates canônicos do agent
codebase-mapper— só a topologia muda.
Output: mesma pasta .planning/codebase/ com os 7 documentos da versão tradicional (STACK, INTEGRATIONS, ARCHITECTURE, STRUCTURE, CONVENTIONS, TESTING, CONCERNS), permitindo diff direto.
Pré-requisitos:
- Claude Code Max / Team / Enterprise (Dynamic Workflows em research preview)
Workflowtool habilitada na sessão- Codebase não-trivial (≥ 5 arquivos de código — o workflow aborta sozinho abaixo disso)
Quando usar PoC ao invés do original:
- Codebase grande onde o mapeamento tradicional toma > 10min ou perde foco
- Você quer confirmação estruturada por mapper (schema) e verificação consolidada dos 7 docs
- Você está validando Dynamic Workflows no kit-mcp antes de migrar outros orquestradores
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.
- 4d ago First seen · 117 lines · 52 tokens per session scan A 95edf54ba495
mapear-codebase-workflow is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,319 once invoked, about $0.0003 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.