legacy-code-safety
100 / 100 · Low risk
Fine to try.
Establish trustworthy feedback around poorly understood or weakly tested existing code before changing it. Use for characterization or approval tests, test-harness access, seams, sensing and separation, dependency breaking, and incremental replacement of risky live code. Once a fast trustworthy boundary exists, use unit-testing to drive the requested new behavior.
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/'legacy-code-safety' ] || [ -L ~/.agents/skills/'legacy-code-safety' ]; then echo 'A skill folder named legacy-code-safety already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Accelerated-Innovation/governed-ai-delivery' "$d" && git -C "$d" checkout --quiet 'f8e8e758b9d5b8cee43ff037245c8c2ec6655b1c' -- 'extensions/otter-skills/skills/legacy-code-safety' && mkdir -p ~/.agents/skills && cp -R "$d"/'extensions/otter-skills/skills/legacy-code-safety' ~/.agents/skills/'legacy-code-safety' && 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/'legacy-code-safety' ~/.claude/skills/'legacy-code-safety' (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/Accelerated-Innovation/governed-ai-delivery/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | f8e8e75 | 100 |
| 2026-11-06 | f8e8e75 | 100 |