isac-multi-agent-consensus
100 / 100 · Low risk
Fine to try.
Use inside the issue agent's triage, implement/followup, and review turns whenever a verdict, root cause, QA list, test tier, design choice, or review decision must come from several independent subagents (investigation angles, cross-critique, consensus or arbiter, fix-until-GREEN review loop, size gate), with unresolved user-level decisions returned as result questions instead of waiting.
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/'isac-multi-agent-consensus' ] || [ -L ~/.agents/skills/'isac-multi-agent-consensus' ]; then echo 'A skill folder named isac-multi-agent-consensus already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/isac322/homelab' "$d" && git -C "$d" checkout --quiet 'a24ab5d6a55a9eb856d8a96fd11544e80a716203' -- 'apps/objects/issue-agent/profile/skills/isac-multi-agent-consensus' && mkdir -p ~/.agents/skills && cp -R "$d"/'apps/objects/issue-agent/profile/skills/isac-multi-agent-consensus' ~/.agents/skills/'isac-multi-agent-consensus' && 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/'isac-multi-agent-consensus' ~/.claude/skills/'isac-multi-agent-consensus' (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/isac322/homelab/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | a24ab5d | 100 |