qp-run
100 / 100 · Low risk
Fine to try.
Automation stage of QP — executes the test cases from qp-plan against the live app through the session's adapter (Playwright MCP for web, computer-use MCP for desktop), records one verdict per step with a closed status, an MTM branch, whether the step was closed by machine evidence or left to judgment, and masks emails/tokens/passwords out of the evidence before saving. Triggers on "run these test cases", "execute the QA plan against the site", "drive the app through the TCs", "TC 실행해줘", "플랜대로 …
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/'qp-run' ] || [ -L ~/.agents/skills/'qp-run' ]; then echo 'A skill folder named qp-run already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/chrono-meta/forge-harness' "$d" && git -C "$d" checkout --quiet 'f87f196702244aa4114c090e71449dbc7695caeb' -- 'plugins/fh-qp/skills/qp-run' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/fh-qp/skills/qp-run' ~/.agents/skills/'qp-run' && 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/'qp-run' ~/.claude/skills/'qp-run' (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/chrono-meta/forge-harness/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | f87f196 | 100 |
| 2026-11-08 | 403f9b9 | 100 |
| 2026-11-06 | 642aabb | 100 |