guard-rsi-score
90 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
One repeatable pass that keeps the RSI loop for `fak guard` actually CLOSING on our own usage - the real, hash-chained decision journal `fak guard` writes - instead of a plan-mode scaffold that never closes. Runs the native guard-RSI scorecard (`fak guard-rsi-scorecard`) over the two guard RSI loops (the hardware-gated LATENCY loop tools/guard_hop_rsi.py and the hardware-free VERDICT loop `fak guard-verdict-rsi`), scores maturity (can it honestly close?) + realized value (does it run on our usa…
What this skill can do
Runs commands on your computer
Connects to the internet
Other copies in this repository
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'guard-rsi-score' ] || [ -L ~/.agents/skills/'guard-rsi-score' ]; then echo 'A skill folder named guard-rsi-score already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/anthony-chaudhary/fak' "$d" && git -C "$d" checkout --quiet '4f8a160935e6bb446c6d346a1770fc1ce42afc29' -- '.agents/skills/guard-rsi-score' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/guard-rsi-score' ~/.agents/skills/'guard-rsi-score' && 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/'guard-rsi-score' ~/.claude/skills/'guard-rsi-score' (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/anthony-chaudhary/fak/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 4f8a160 | 90 |
| 2026-11-09 | 22403c3 | 90 |
| 2026-11-07 | b2c2791 | 90 |