AARM Policy Layer

by safedep

AARM Policy Layer is an AI Engineering skill for Claude Code, published by safedep in gryph.

161 stars18 forkson safedep/gryphAdded 2026/09/08Repository updated 2026/08/30

View source on GitHub Download repo ZIP

ai-agentsai-developer-toolsclaude-codegemini-clisecurity

Install in seconds

Install AARM Policy Layer

Copy AARM Policy Layer into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/safedep/gryph/tree/main/.claude/skills/aarm-policy-layer ~/.claude/skills/aarm-policy-layer

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/safedep/gryph.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/aarm-policy-layer/SKILL.md in safedep/gryph
Installs to: ~/.claude/skills/aarm-policy-layer
Collection: One of 3 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What AARM Policy Layer does

AARM Policy Layer covers Gryph’s security policy engine, including policy evaluation, receipts, context accumulation, approvals, and identity capture. Use it when changing AARM code, policy YAML, or CLI policy wiring.

AARM Policy Layer is cataloged under AI Engineering on DirSkills. AARM Policy Layer comes from a repository tagged ai-agents, ai-developer-tools, claude-code, gemini-cli and security.

Documentation

README

Excerpt

AARM / Policy Layer

The full, current guide is docs/aarm-dev.md. It is the single source of truth for this task. Read it and follow it step by step.

Do not change the AARM layer from memory. The layer spans about 15 packages under aarm/, plus the wiring in cli/policy.go. The request flow chains a normalize step, an identity gate, the context accumulator, the PDP, a decision branch, and a receipt write. A change in one step can break another. The doc maps the flow, the packages, and the extension points.

How to use this skill

This is the opening of the README. Read the full README on GitHub.

Frequently asked about AARM Policy Layer

What else does safedep publish alongside AARM Policy Layer?
AARM Policy Layer is one of 3 skills that DirSkills catalogs from safedep/gryph, the repository it ships in. Its siblings there include Add Agent Adapter and Gryph Policy Authoring. Each one is a separate skill with its own page in this directory, installs the same way AARM Policy Layer does, and is maintained by safedep in that same repository. The rest of the collection is listed on the safedep/gryph page.
How does AARM Policy Layer compare to other AI Engineering skills?
AARM Policy Layer ranks #3401 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of AARM Policy Layer against them. Open each page to compare what they document and how they install.