controlflow-review
Use after implementation to review a diff or completed phase. A thin ControlFlow layer over Claude Code's native /code-review: adds plan-vs-implementation…
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
$ npx -y skills add Smithbox-ai/ControlFlow --skill controlflow-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/controlflow-planContext preview
The summary Claude sees to decide when to auto-load this skill.
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
name: controlflow-plan description: "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."
Produce a durable, execution-ready plan in the shared ControlFlow format. The format is not restated here: it is single-sourced from `schemas/planner.plan.schema.json` (the machine-enforced contract) and `plans/templates/plan-document-template.md` (the human document skeleton). Read both at invoke time and conform to them; do not paraphrase the contract from memory.
Invoke this skill via `/controlflow-claude-code:controlflow-plan`.
assumptions with a bounded scope statement.
handoff without depending on plugin-host runtime contracts.
assumption, simplicity, scope, and verification discipline.
architecture, or destructive-risk handling; otherwise record a bounded assumption.
1. Create a saved plan when the user asks for one or when work is SMALL, MEDIUM, or LARGE; skip only for truly TRIVIAL work. Save to `plans/<task-slug>-plan.md` unless the user names another path. 2. Read `schemas/planner.plan.schema.json` and `plans/templates/plan-document-template.md` — these are the authoritative format. Use [references/plan-format.md](references/plan-format.md) as a compact checklist, not a substitute for them. 3. Map likely files, tests, commands, dependencies, and change boundaries before phase decomposition. 4. Read [references/complexity-tiers.md](references/complexity-tiers.md); assign one tier. Any unresolved HIGH-impact semantic risk forces LARGE regardless of file count. 5. Fill all seven semantic risk categories (see [references/plan-format.md](references/plan-format.md)); never skip a row — use `not_applicable` with justification. 6. Write the artifact using the template's header, 10 sections in order, and the five lifecycle sections (`## Progress`, `## Discoveries`, `## Decision Log`, `## Outcomes`, `## Idempotence & Recovery`) for SMALL+ plans. 7. Every phase declares exactly one `executor_agent` from the schema enum, lists concrete files, tests, acceptance criteria, quality gates, and failure expectations, and keeps steps in numbered prose with NO code blocks. 8. Add Mermaid diagrams per tier: `sequenceDiagram` for MEDIUM+ non-trivial orchestration; `flowchart TD` + `sequenceDiagram` for LARGE. Each diagram ≤30 lines. 9. Set `status: ABSTAIN` or `REPLAN_REQUIRED` when confidence is below 0.9 or evidence is insufficient; include the terminal-outcome structure from the template. 10. Add a research or spike phase before implementation when a HIGH-impact risk is unresolved. 11. For `READY_FOR_EXECUTION`, include a Handoff section pointing execution to `plans/<task-slug>-plan.md` — do NOT inline the plan in chat. See [references/inline-execution.md](references/inline-execution.md) for how execution treats waves, the context packet, and optional delegation.
Hand non-TRIVIAL plans to `/controlflow-claude-code:controlflow-verify`, which runs inline adversarial verification: SMALL → phase 1; MEDIUM → phases 1–2; LARGE → phases 1–3.
A multi-agent orchestration system for VS Code Copilot, plus maintained Codex, Claude, and Cursor plugins.
Repo: Smithbox-ai/ControlFlow
Use after implementation to review a diff or completed phase. A thin ControlFlow layer over Claude Code's native /code-review: adds plan-vs-implementation…
Use after /controlflow-claude-code:controlflow-plan produces a plan, before implementation. Runs adversarial pre-execution verification inline in the main…