controlflow-orchestration
Use when executing an approved multi-phase plan in Cursor, with gates, approvals, retries, and Task delegation to controlflow subagents.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when executing an approved multi-phase plan in Cursor, with gates, approvals, retries, and Task delegation to controlflow subagents.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when a non-trivial repository task needs a durable, execution-ready ControlFlow plan before coding, especially for cross-file changes, migrations, architectural uncertainty, or explicit risk review.
Use after implementation when a ControlFlow plan exists and review should focus on plan conformance, scope drift, evidence-backed correctness findings, and residual validation gaps rather than duplicating native Codex /review.
Use after a ControlFlow plan is saved and before implementation. Runs tier-gated adversarial verification inline: structural audit, assumption/mirage detection, and cold-start executability simulation.
Use when a repository task needs a high-quality ControlFlow plan before coding — small, medium, or large scope, cross-file edits, risky migrations, architectural uncertainty, or any work that should produce a saved Markdown plan artifact in plans/. Single-sources the plan format from schemas/planner.plan.schema.json and the plan template.
Use when a saved plan may contain hidden assumptions disguised as facts, especially for medium or large tasks, unresolved high-risk plans, or plans that mention files, APIs, versions, integrations, tests, or concurrency patterns that should be verified against the repository before execution.
Use when a saved plan should be tested for cold-start executability before coding, especially for large tasks, weak-confidence plans, or plans whose early phases may be too vague for a fresh executor to follow without hidden context.
| name | controlflow-orchestration |
| description | Use when executing an approved multi-phase plan in Cursor, with gates, approvals, retries, and Task delegation to controlflow subagents. |
Execute an approved plan with explicit state, disciplined gates, bounded retries, and local evidence. Does not use VS Code agent/runSubagent.
plans/<task-slug>-plan.md; use controlflow-planning if missing.SMALL → plan audit; MEDIUM/LARGE → assumption verifier; LARGE → executability verifier; HIGH risk → assumption verifier.executor_agent, prefer Task to the matching .cursor/agents/controlflow-*.md subagent. Parent must not implement when an implementer subagent is assigned.references/failure-taxonomy.md and references/runtime-policy.json for retry/replan.plans/artifacts/<task-slug>/.| Phase role | subagent_type |
|---|---|
| CodeMapper | controlflow-code-mapper |
| Researcher | controlflow-researcher |
| Core implementer | controlflow-core-implementer |
| UI implementer | controlflow-ui-implementer |
| Platform | controlflow-platform-engineer |
| Docs | controlflow-technical-writer |
| Browser test | controlflow-browser-tester |
| Code review gate | controlflow-code-reviewer |
Fallback: Execute the role instructions in the parent session using the matching skill; record that fallback in the plan ## Decision Log.
Stop when verification fails, assumptions break, security risk appears, or approval is missing. Classify failures per failure taxonomy before retry.
references/runtime-policy.jsonreferences/failure-taxonomy.mdreferences/phase-checklist.mddocs/agent-engineering/CURSOR-SUPPORT.md