audit-decisions
100 / 100 · Low risk
Fine to try.
Audit the decisions an implementing agent made, not its diff — a pure audit that traces the session's history into a decisions ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'audit-decisions' ] || [ -L ~/.agents/skills/'audit-decisions' ]; then echo 'A skill folder named audit-decisions already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/dzhng/skills' "$d" && git -C "$d" checkout --quiet '828e386301530b406b2fbd6d48136eae75720262' -- 'skills/engineering/audit-decisions' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/engineering/audit-decisions' ~/.agents/skills/'audit-decisions' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'audit-decisions' ~/.claude/skills/'audit-decisions' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/dzhng/skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-10 | 828e386 | 100 |
| 2026-11-08 | a4076b7 | 100 |
| 2026-11-07 | a4076b7 | 100 |