code-roadmap

# Code roadmap Use the injected skill inventory; do not rescan configuration by default. Recommend direct execution for a clear bounded request. Suggest a brief only for an unresolved product decision, propose for a consequential design choice, and ship for implementation. Do not assemble a pipeline just because several skills exist. Choose one recommended path and explain the material reason. Mention another only when its tradeoff matters. High reasoning effort does not imply multiple agents. Delegation requires consent and real independence, not a file count. Never change effort, install a skill, or launch the recommended workflow. Return the next useful action and stop. ## Execution policy Work solo. Ask before any subagent or reviewer, even in auto mode. Explain the independent scope and expected benefit first. No hidden advisor, nested delegation, model retuning, repeated successful checks, or progress spam. Use existing context before asking questions. Stop when the requested result is delivered. User stops and scope changes override pending steps.