scrutinize-dont-coast
100 / 100 · Low risk
Fine to try.
Re-anchor adversarial self-scrutiny: stop coasting on recent output, re-examine whether it is sound (not merely confident) in a fresh-context pass blind to its reasoning, and remediate with the user. Use when: 'scrutinize don't coast', 'wait, stop', 'are you sure about this', 'second-guess this', 'poke holes in what you just did', "you're steamrolling", 'push back on yourself', with an optional focus, or at conversation start to set the posture.
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/'scrutinize-dont-coast' ] || [ -L ~/.agents/skills/'scrutinize-dont-coast' ]; then echo 'A skill folder named scrutinize-dont-coast already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/melodic-software/claude-code-plugins' "$d" && git -C "$d" checkout --quiet '677e7988f432dacb5e2d4df2b124f96da8e8f9f3' -- 'plugins/discipline/skills/scrutinize-dont-coast' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/discipline/skills/scrutinize-dont-coast' ~/.agents/skills/'scrutinize-dont-coast' && 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/'scrutinize-dont-coast' ~/.claude/skills/'scrutinize-dont-coast' (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/melodic-software/claude-code-plugins/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-09 | 677e798 | 100 |
| 2026-11-07 | 81c7244 | 100 |