aarm-policy-layer
100 / 100 · Low risk
Fine to try.
Use when working on Gryph's AARM security layer or policy engine. Trigger this whenever the user changes code under aarm/, engine/policy.go or cli/policy.go, or works on policy evaluation, the PDP, policy rules, CEL conditions, receipts and the receipt hash chain, receipt signing, the context accumulator, approvals, deferrals, identity capture, data classification, injection scoring, or the self-protection rules. Also trigger on phrases like "policy engine", "policy decision point", "AARM", "re…
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/'aarm-policy-layer' ] || [ -L ~/.agents/skills/'aarm-policy-layer' ]; then echo 'A skill folder named aarm-policy-layer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/safedep/gryph' "$d" && git -C "$d" checkout --quiet 'ad731d09e70e51fc57c4ada156111324292adf0e' -- '.claude/skills/aarm-policy-layer' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/aarm-policy-layer' ~/.agents/skills/'aarm-policy-layer' && 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/'aarm-policy-layer' ~/.claude/skills/'aarm-policy-layer' (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/safedep/gryph/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-14 | ad731d0 | 100 |
| 2026-11-07 | 9cc05b5 | 100 |