ControlFlow Executability Verifier
Simulates a saved plan's first tasks cold-start to catch vague phases before coding starts.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 67a5236
Ran a vague 3-phase 'add rate limiting' plan through it: it correctly stopped at Phase 1 (no framework/target file named) and refused to guess, producing a structured FAIL verdict a freeform review didn't match in rigor -- but step 6's save path points at ../../templates/executability-verifier-report-template.md, a file that does not exist anywhere in the source repo.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What ControlFlow Executability Verifier does
Walks a saved implementation plan through an 8-point clarity checklist and a TDD-style walkthrough, stopping at the first real blocker instead of assuming intent. Trigger it before starting on a large or low-confidence plan, or whenever the early phases might be too vague for a fresh executor to follow without hidden context.
How to install ControlFlow Executability Verifier
git clone https://github.com/Smithbox-ai/ControlFlow.git
mkdir -p ~/.claude/skills
cp -r ControlFlow/.cursor/skills/controlflow-executability-verifier ~/.claude/skills/controlflow-executability-verifier
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger ControlFlow Executability Verifier
-
/controlflow-executability-verifierSimulates a saved plan's first tasks cold-start to catch vague phases before coding starts.
It also activates on plain-language prompts like these:
-
Before I start coding, check if Phase 1 of this plan is too vague -
Walk through my saved implementation plan like a fresh executor would -
Stress-test this rate-limiting plan for hidden context gaps
Frequently asked questions
- Is the ControlFlow Executability Verifier skill free?
- Yes. The skill itself is free from Smithbox-ai/ControlFlow. SkillProof publishes the install command and an independent test verdict at no cost.
- Does ControlFlow Executability Verifier work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Ran a vague 3-phase 'add rate limiting' plan through it: it correctly stopped at Phase 1 (no framework/target file named) and refused to guess, producing a structured FAIL verdict a freeform review didn't match in rigor -- but step 6's save path points at ../../templates/executability-verifier-report-template.md, a file that does not exist anywhere in the source repo.
- What is the ControlFlow Executability Verifier SkillProof Score?
- 8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install ControlFlow Executability Verifier?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use ControlFlow Executability Verifier with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.