Plan Review Gate

Plan Review Gate is an AI Engineering skill for Claude Code, published by romiluz13 in cc10x.

164 stars25 forkson romiluz13/cc10xAdded 2026/09/08Repository updated 2026/08/03

agent-harnessclaude-codeclaude-code-plugincontext-engineeringharness-engineeringllm-agentsloop-engineeringorchestrationtest-honesty

Install in seconds

Install Plan Review Gate

Copy Plan Review Gate into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/romiluz13/cc10x/tree/main/plugins/cc10x/skills/plan-review-gate ~/.claude/skills/plan-review-gate

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/romiluz13/cc10x.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/cc10x/skills/plan-review-gate/SKILL.md in romiluz13/cc10x
Installs to: ~/.claude/skills/plan-review-gate
Collection: One of 21 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Plan Review Gate does

Plan Review Gate checks saved plans and decision RFCs for feasibility, completeness, and alignment before execution. It is used after non-trivial planning when a fail-closed review should block unsafe or incomplete work.

Plan Review Gate is cataloged under AI Engineering on DirSkills. Plan Review Gate comes from a repository tagged agent-harness, claude-code, claude-code-plugin, context-engineering and harness-engineering.

Documentation

README

Excerpt

Spec Review Gate

Core principle: No execution plan or decision RFC reaches the user without surviving adversarial scrutiny. No leniency. "Close enough" is FAIL. A structurally neat but repo-wrong plan is FAIL.

How it works: This skill runs inline in the calling agent's context (no subagents). The calling LLM acts as an independent auditor, reads the saved artifact, and checks it against 3 criteria using Read/Grep/Glob. The value is fail-closed blocking and adversarial framing, not reviewer isolation — keep the auditor posture, but do not claim independence the gate doesn't have.

When to Skip

Skip when artifact is truly trivial: Single-file fix, copy edit, or config tweak with <3 changes and no architecture choice → return SPEC_GATE_PASS immediately.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Plan Review Gate

What else does romiluz13 publish alongside Plan Review Gate?
Plan Review Gate is one of 21 skills that DirSkills catalogs from romiluz13/cc10x, the repository it ships in. Its siblings there include Agent Common, Architecture and Building. Each one is a separate skill with its own page in this directory, installs the same way Plan Review Gate does, and is maintained by romiluz13 in that same repository. The rest of the collection is listed on the romiluz13/cc10x page.
How does Plan Review Gate compare to other AI Engineering skills?
Plan Review Gate ranks #3383 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Plan Review Gate against them. Open each page to compare what they document and how they install.