rokurolize-codex-skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rokurolize-codex-skills (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Reusable Agent Skills for OpenAI Codex and other agents that support the SKILL.md format.
This repository is structured for multiple skills. The first published skill is root-cause-analysis, an evidence-backed RCA / postmortem / なぜなぜ分析 workflow.
| Skill | Path | Purpose |
|---|---|---|
root-cause-analysis | skills/root-cause-analysis/ | Perform serious root cause analysis with evidence ledgers, causal branches, counterfactual tests, concrete fix surfaces, and verification gates. |
Inside Codex, install the skill from its GitHub directory URL:
$skill-installer install https://github.com/Rokurolize/codex-skills/tree/main/skills/root-cause-analysisThen restart Codex if the skill does not appear immediately.
For plugin-oriented distribution, this repository also includes .codex-plugin/plugin.json and a repo marketplace entry at .agents/plugins/marketplace.json. The plugin currently bundles the same one skill and is ready to grow as more skills are added.
This repo intentionally uses a simple personal-publisher structure:
.codex-plugin/plugin.json
.agents/plugins/marketplace.json
skills/
root-cause-analysis/
SKILL.md
LICENSE.txt
agents/openai.yaml
references/
scripts/
tests/The layout follows the public OpenAI skill/package conventions where they are useful: each skill is a folder with SKILL.md, optional agents/openai.yaml, optional references, and optional scripts. It does not copy OpenAI's .curated or .experimental categories because those labels are catalog policy inside openai/skills, not useful taxonomy for an individual publisher.
Run the skill's built-in audit self-test:
python3 skills/root-cause-analysis/scripts/root_cause_analysis_audit.py --self-testRun the repository tests:
python3 -m pytestMIT. See LICENSE and each skill's LICENSE.txt.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.