---
title: "adversarial-plan-approval"
description: "Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task or decision gate."
canonical: https://agentpluginsdirectory.com/plugins/adversarial-plan-approval
last-updated: 2026-10-21
---

# adversarial-plan-approval
Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task or decision gate.
- Slug: adversarial-plan-approval
- Publisher: Abdeslam Yassine Agmar
- Repository: https://github.com/ayagmar/agents-skills
- Manifest: plugins/adversarial-plan-approval/plugin.json
- Version: 0.1.2
- License: MIT
- Category (editorial): other
- Skills: 1 (adversarial-plan-approval)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-09-28
- Repository last pushed: 2026-10-20
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/adversarial-plan-approval
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What adversarial-plan-approval does, in the publisher's words

Review, challenge, or approve an implementation plan before work starts. Privacy: instruction-only skill; ships no scripts, reads no session stores, and makes no network requests of its own.

- None beyond a coding agent that supports Agent Skills

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/ayagmar/agents-skills/HEAD/plugins/adversarial-plan-approval/README.md

## Skills

- adversarial-plan-approval: Independently falsify or approve implementation plans before execution, issuing ACCEPT / MODIFY / REJECT verdicts per task or decision gate. Use when asked to review, challenge, vet, or approve a plan, program, or task board before work starts. Not for authoring plans (implementation-plan-author),…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.