codex-readiness-unit-test

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

1|Updated Oct 12, 2022

Search Tags:#codex #reporting #evidence #unit-test #deterministic #readiness #LLM-evaluation

Ready to run

npx skills add https://github.com/plastikaweb/plastikspace --skill codex-readiness-unit-test

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codex-readiness-unit-test
Source: https://github.com/plastikaweb/plastikspace/tree/main/.agent/skills/codex-readiness-unit-test
Command: npx skills add https://github.com/plastikaweb/plastikspace --skill codex-readiness-unit-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates Codex readiness assessment by collecting evidence and running structured checks against onboarding documentation to produce a reproducible report.

Core Features & Use Cases

Collects filesystem and repository signals from AGENTS.md and PLANS.md to surface evidence for LLM evaluation.
Runs deterministic readiness rules to validate presence of key files (AGENTS.md, plans references, config.toml) and to summarize execution outcomes when plans are executed.
Generates a comprehensive report and a scorecard to inform onboarding quality and readiness.

Quick Start

Run evidence collection: python .agent/skills/codex-readiness-unit-test/scripts/collect_evidence.py
Validate with deterministic checks: python .agent/skills/codex-readiness-unit-test/scripts/deterministic_rules.py
Optionally execute a documented plan and generate a score: python .agent/skills/codex-readiness-unit-test/scripts/run_plan.py --plan .codex-readiness-unit-test/<timestamp>/plan.json
Produce the final report: python .agent/skills/codex-readiness-unit-test/scripts/scoring.py --mode read-only

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 automate codex readiness evaluation for onboarding documentation?▼

Automating codex readiness evaluation involves collecting evidence from AGENTS.md and PLANS.md, then executing deterministic checks to generate a reproducible onboarding readiness scorecard.

What is a deterministic readiness check for monorepo documentation?▼

Deterministic readiness checks validate the presence of key files like AGENTS.md, plans references, and config.toml in monorepos to produce consistent, rule-based evidence for LLM evaluation.

How do I generate a readiness scorecard from AGENTS.md and PLANS.md?▼

You generate a readiness scorecard by running modular Python scripts to gather evidence, validate deterministic rules, and optionally execute documented plans to render a final scoring report.

Do I need Python to run deterministic checks on Codex docs?▼

Yes, you need Python to execute the modular scripts that collect evidence and run deterministic readiness rules against your Codex onboarding documentation.

Can I execute documented plans and generate a readiness score in read-only mode?▼

Yes, you can execute a documented plan via a JSON file and subsequently generate a readiness score in read-only mode using the provided scoring script.

What are the limitations of using deterministic rules for LLM evaluation evidence?▼

Deterministic rules are limited to validating file presence and summarizing plan execution outcomes, providing structural evidence rather than performing the qualitative LLM evaluation itself.