Skip to content
Back to skills

Controlflow Plan Audit

ASecurity

Use when a saved implementation plan should be adversarially reviewed before coding, especially for small, medium, or large tasks that may contain architecture flaws, scope gaps, destructive risk, weak rollback, weak tests, or dependency conflicts.

  • 13 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added May 27, 2026
data-aiawssecurity

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add Smithbox-ai/ControlFlow --skill controlflow-plan-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Controlflow Plan Audit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Controlflow Plan Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/smithbox-ai-controlflow-plan-audit/badge)](https://www.skillsdirectory.com/skills/smithbox-ai-controlflow-plan-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: controlflow-plan-audit
description: "Use when a saved implementation plan should be adversarially reviewed before coding, especially for small, medium, or large tasks that may contain architecture flaws, scope gaps, destructive risk, weak rollback, weak tests, or dependency conflicts."
---

# ControlFlow Plan Audit

## Overview

Adversarially review a saved implementation plan before coding. Look for architecture defects, dependency mistakes, missing rollback, scope gaps, weak tests, and first-phase executability problems.

## Local Contract

- Read the actual plan artifact and cross-check it against repository files, tests, commands, architecture, and dependencies.
- Use [references/audit-checklist.md](references/audit-checklist.md) for audit coverage and [../controlflow-planning/references/llm-behavior-guidelines.md](../controlflow-planning/references/llm-behavior-guidelines.md) for generic evidence discipline.
- Save the verdict to `plans/artifacts/<task-slug>/plan-audit.md` using [../../templates/plan-audit-report-template.md](../../templates/plan-audit-report-template.md).
- Tie findings to plan sections or repository facts.

## Workflow

1. Read the saved plan artifact first, not a summary.
2. Check file/path reality, available tests and validation commands, architecture/dependency surfaces, rollback, acceptance quality, contract completeness, and first-phase executability.
3. Return one verdict: `APPROVED`, `NEEDS_REVISION`, `REJECTED`, or `ABSTAIN`.
4. For non-approval, classify as `fixable`, `needs_replan`, or `escalate`.
5. Save and summarize evidence-backed findings.

## Spec-Before-Plan Health Check

For non-trivial work, confirm the plan is anchored to explicit requirements, acceptance criteria, constraints, exclusions, and verification gates rather than inferred chat context.

## Audit-Specific Failure Checks

- Do not approve a detailed plan that lacks a spec artifact or equivalent requirements section.
- Do not approve vague success criteria; require measurable acceptance and gates.
- Do not downplay rollback gaps; classify them by blast radius.
- Do not accept plausible repository claims without checking current paths and commands.

## Output Shape

- **Status**
- **Findings**
- **Risk Summary**
- **Recommendation**
- **Failure Classification** when needed
- **Confidence**

## References

- `references/audit-checklist.md`
- `../../templates/plan-audit-report-template.md`
- `../controlflow-review/references/security-review-discipline.md`
- `../controlflow-planning/references/llm-behavior-guidelines.md`

Files in this skill

  • SKILL.md2.6 KB
  • references/audit-checklist.md826 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.