skills.rest
pchemguy
pchemguyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

codex-readiness-unit-test

Run filesystem-based Codex readiness checks with in-session LLM evaluation.

Updated Feb 4, 2026
Search Tags:#unit-test#deterministic#repo-analysis#llm-evaluation#evidence-collection#codex-readiness
One-click install
npx skills add https://github.com/pchemguy/Dummy --skill codex-readiness-unit-test-pchemguy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex-readiness-unit-test
Source: https://github.com/pchemguy/Dummy/tree/main/docs/AgentSkills/openai/skills/skills/.experimental/codex-readiness-unit-test
Command: npx skills add https://github.com/pchemguy/Dummy --skill codex-readiness-unit-test-pchemguy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run deterministic, filesystem-based Codex readiness checks with in-session evaluation of AGENTS.md and PLANS.md, enabling quick, reproducible readiness assessment without external API calls.

Core Features & Use Cases

  • Deterministic evidence collection from the repository cwd.
  • In-session LLM evaluation of AGENTS.md/PLANS.md for readiness scoring.
  • Generates a structured report and summary suitable for audits or PR reviews.

Quick Start

Collect evidence, run deterministic rules, and perform in-session LLM checks to generate the Codex readiness report.

Frequently Asked Questions about codex-readiness-unit-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run deterministic Codex readiness checks for my repository?▼

Run deterministic Codex readiness checks by executing filesystem-based rules and in-session LLM evaluation on your repository's current working directory, generating evidence and readiness results without external API calls.

What is in-session LLM evaluation for repository readiness?▼

In-session LLM evaluation for repository readiness is a mechanism that scores your AGENTS.md and PLANS.md files locally, producing evidence collections and structured reports without relying on external API calls.

How do I assess AGENTS.md and PLANS.md readiness without external API calls?▼

Assess AGENTS.md and PLANS.md readiness without external API calls by using in-session LLM evaluation to perform deterministic filesystem checks and generate structured readiness summaries.

Does the Codex readiness check work across multiple repositories or monorepos?▼

The Codex readiness check does not work across monorepos; it operates relative to the current working directory of a single repository and performs no monorepo discovery.

Where are Codex readiness unit test results stored?▼

Codex readiness unit test results are stored in the .codex-readiness-unit-test/<timestamp>/ directory, with the latest summary updating .codex-readiness-unit-test/latest.json.

Can I use Codex readiness checks for PR reviews and audits?▼

You can use Codex readiness checks for PR reviews and audits because the tool generates structured reports and summaries from deterministic evidence collection and in-session LLM evaluation.

Related Skills

Explore More Software Engineering Skills→
lane2077lane2077

session-init

Initialize Claude Code sessions by checking environment and summarizing task state.

Community
Intermediate
Pear-CommercePear-Commerce

tech-log-test-failure-watcher

Monitor Slack #tech-log for api.pearcommerce.com test failures and triage them.

Official
Advanced
plastikawebplastikaweb
1

codex-readiness-unit-test

Collect evidence and run deterministic checks against AGENTS.md and PLANS.md to generate readiness reports.

Community
Advanced
adzcsx2adzcsx2
1

dt:codex-sync-push

Synchronize and push Codex configuration, hooks, prompts, and user skills to a remote repository.

Community
Advanced