Review test case sufficiency using Codex MCP, suggest additional edge cases. Supports review loop with context preservation.
Scanned 9/4/2026
Install to Claude Code
Skills Directorynpx -y skills add sd0xdev/sd0x-harness --skill codex-test-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Codex Test Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/sd0xdev-codex-test-review-sd0x-harness)More formats (shields.io, HTML) on the badges page.
---
name: codex-test-review
description: "Review test case sufficiency using Codex MCP, suggest additional edge cases. Supports review loop with context preservation."
allowed-tools: mcp__codex__codex, mcp__codex__codex-reply, Bash(git:*), Read, Grep, Glob
---
# Codex Test Review
Thin entry-point skill — routes to the parent skill for full workflow.
## Parent Skill
This skill delegates to `test-review` for the full test coverage review workflow, prompt templates, and sufficiency assessment.
See `@skills/test-review/SKILL.md`
## Variant
This is the **Review** variant — evaluates existing test coverage and suggests gaps.
## Trigger
- Keywords: test review, review tests, test coverage, test sufficiency, codex-test-review
## When NOT to Use
- Generating new tests (use `/codex-test-gen`)
- Code review (use `/codex-review-fast`)
- Security audit (use `/codex-security`)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
