Menu
Use before planning non-trivial Codex work when the requirements, acceptance criteria, boundaries, constraints, or success measures are not yet clear enough for a safe implementation plan.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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-spec |
| description | Use before planning non-trivial Codex work when the requirements, acceptance criteria, boundaries, constraints, or success measures are not yet clear enough for a safe implementation plan. |
Capture a short, durable specification before $controlflow-planning. The spec records the outcome, exclusions, success proof, constraints, and unresolved questions so planning does not infer requirements from loose chat context.
Use $controlflow-spec before $controlflow-planning when:
SMALL, MEDIUM, or LARGE and no accepted spec existsSkip this skill for TRIVIAL fixes where the expected behavior and verification command are already explicit.
plans/artifacts/<task-slug>/spec.md, unless the user gives another path.$controlflow-planning with spec_path and intended plan_path.# Spec: <task name>
## Objective
<What outcome is needed and why it matters.>
## In-Scope
<Files, workflows, behaviors, or artifacts that planning may include.>
## Out-of-Scope
<Related work that must not be absorbed into this effort.>
## Acceptance Criteria
<Observable conditions that must be true when the work is done.>
## Constraints
<Compatibility, governance, source-use, security, dependency, schedule, or verification limits.>
## Success Metrics
<Commands, review gates, artifacts, or measurable outcomes that prove completion.>
## Risks/Open Questions
<Unresolved assumptions, unknowns, and questions that block or shape planning.>
After writing the spec artifact, invoke $controlflow-planning with a concise handoff that includes:
spec_path: the saved Markdown spec artifactplan_path: the intended plan artifact, usually plans/<task-slug>-plan.mdExample handoff phrasing:
Use $controlflow-planning to create plan_path=plans/<task-slug>-plan.md from spec_path=plans/artifacts/<task-slug>/spec.md.
If the request is still ambiguous after one clarification round, stop before planning. Ask the smallest set of blocking Codex-local questions, explain which planning decision each answer controls, and do not call $controlflow-planning until the answer is available or the user explicitly accepts a documented assumption.