New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Aarm Policy Layer

by safedep in safedep/gryph

A skill your agent uses when working on Gryph's AARM security layer or policy engine.

Apache-2.0Auto-check passedBackend & APIs

Install Aarm Policy Layer

skills CLI
$ npx skills add safedep/gryph --skill aarm-policy-layer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install safedep/gryph aarm-policy-layer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/safedep/gryph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/aarm-policy-layer .claude/skills/aarm-policy-layer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aarm-policy-layer
GitHub stars
172
Token cost
~921 tokens
SKILL.md length
466 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when working on Gryph's AARM security layer or policy engine.

  • Works in 4 steps: Read docs/aarm-dev.md in full. → Use the package map to find the right… → Add a Mediator dependency through a… → …
  • Working on Gryphs AARM security layer
  • SKILL.md covers How to use this skill, Invariants, Keep the doc correct and Keep the user-facing policy…
  • Calls make

What it does

Aarm Policy Layer is an agent skill from safedep/gryph. Use when working on Gryph's AARM security layer or policy engine. Trigger this whenever the user changes code under aarm/ 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", "receipt chain", "gryph policy", "policy…

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Authorization and RBAC. The repository describes itself as: Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more. The licence is Apache-2.0.

When your agent uses it

  • Working on Gryphs AARM security layer
  • This whenever the user changes code under aarm/
  • Works on policy evaluation
  • Receipts and the receipt hash chain

Example prompts

  • “policy engine”
  • “policy decision point”
  • “receipt chain”
  • “/aarm-policy-layer”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read docs/aarm-dev.md in full.
  2. Use the package map to find the right package for your change.
  3. Add a Mediator dependency through a MediatorOption in aarm/check.go, then wire it in loadPolicyMediator in cli/policy.go.
  4. Run make test and make lint before you finish. Run make generate-schema after any change to the policy schema or a payload type.

What it can do on your machine

Read from SKILL.md and the folder at commit 426480f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Aarm Policy Layer loads about 921 tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 466 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~921

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from safedep/gryph at commit 426480f, republished under its Apache-2.0 licence (© safedep). 466 words, ~921 tokens.

Download SKILL.mdSave it as .claude/skills/aarm-policy-layer/SKILL.md (or your agent's skills folder).
name
aarm-policy-layer
description
Use when working on Gryph's AARM security layer or policy engine. Trigger this whenever the user changes code under aarm/ 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", "receipt chain", "gryph policy", "policy rule", or "context accumulator", even when the user does not name a file.

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

  1. Read docs/aarm-dev.md in full.
  2. Use the package map to find the right package for your change.
  3. Add a Mediator dependency through a MediatorOption in aarm/check.go, then wire it in loadPolicyMediator in cli/policy.go.
  4. Run make test and make lint before you finish. Run make generate-schema after any change to the policy schema or a payload type.

Invariants

Three invariants break silently if you miss them. The doc explains all three.

  1. The receipt and context hashes are consensus formats. A change to field order or canonicalization breaks every existing chain. Update the verifier and the property tests in the same change.
  2. The aarm package stays decoupled from storage and cli. Carry CLI-shaped side effects through the hooks (DeferralHook, ApprovalAuditHook, IdentityAuditHook). Do not add a storage or cli import to aarm.
  3. Policy resolution is additive and same-user safe. disabled: is scoped to the file that declares the rule, block always beats allow, and no user file can disable a built-in. Keep these when you touch Loader.Load or the merge, so an installed policy file can never remove the built-in rules or another file's rules. See docs/security-policy-threat-model.md.
Show full SKILL.md (182 more words)Show less

Keep the doc correct

The doc is the source of truth, so keep it accurate. If you find the code no longer matches the doc, update docs/aarm-dev.md in the same change. Do not fork the guidance into this skill.

Keep the user-facing policy doc fresh

docs/security-policy.md is the user-facing guide for policy authors. Whenever you make a UX-related change in the policy layer, update it in the same change. UX-related changes include:

  • New, renamed, or removed gryph policy ... commands or flags (init, edit, list, install, validate, test, receipts, context, deferrals, approve, keys).
  • Changes to the policy YAML surface: rule fields, match criteria, CEL variables, decisions, or the disabled: mechanism.
  • Changes to configuration keys under policy: in the config file, or to their defaults.
  • Changes to default behavior a user can observe: sign modes, fail modes, retention, auto-defer triggers, approval prompts, block or guidance message format.
  • Changes to file locations the user interacts with: policy.yaml, the policies/ directory, the keys directory, the trust store.

Keep docs/aarm-dev.md for internals and docs/security-policy.md for the user surface. A change that touches both layers updates both docs.

© safedep, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/aarm-policy-layer of safedep/gryph.

Open the folder on GitHubat commit 426480f

Compare with similar skills

Aarm Policy Layer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Aarm Policy Layer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aarm Policy Layer this skillsafedep/gryph172—~921Automated safety check: PassApache-2.0
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
K8s Security PoliciesCybereason-Public/owLSM28012 repos~2kAutomated safety check: PassGPL-2.0
Payloadpayloadcms/payload45k5 repos~6.2kAutomated safety check: PassMIT
Convex Setup Authspokvulcan/poker-planning1148 repos~1.8kAutomated safety check: PassMIT
Cognitoitsmostafa/aws-agent-skills1.2k1 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed

  • K8s Security Policies

    Cybereason-Public/owLSM

    Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.

    280 GitHub starsUsed in 12 repos~2k tokens
    Backend & APIsAuto-check passed

  • Payload

    payloadcms/payload

    A skill your agent uses when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API).

    45k GitHub starsUsed in 5 repos~6.2k tokens
    Backend & APIsAuto-check passed

  • Convex Setup Auth

    spokvulcan/poker-planning

    Sets up Convex auth, identity mapping, and access control. An agent skill from spokvulcan/poker-planning.

    114 GitHub starsUsed in 8 repos~1.8k tokens
    Backend & APIsAuto-check passed

  • Cognito

    itsmostafa/aws-agent-skills

    AWS Cognito user authentication and authorization service. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub starsUsed in 1 repo~2.3k tokens
    Backend & APIsAuto-check passed

  • Abp Authorization

    abpframework/abp

    ABP permission system - PermissionDefinitionProvider, [Authorize] attribute, CheckPolicyAsync, IsGrantedAsync, ICurrentUser, IPermissionManager, multi-tenancy side.

    14k GitHub stars~1.3k tokensUpdated today
    Backend & APIsAuto-check passed

More from safedep/gryph

  • Add Agent Adapter

    safedep/gryph

    A skill your agent uses when adding support for a new AI coding agent to Gryph, or when changing how an existing agent adapter is wired.

    172 GitHub stars~679 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Aarm Policy Layer

What does Aarm Policy Layer do?

A skill your agent uses when working on Gryph's AARM security layer or policy engine. Aarm Policy Layer is an agent skill from safedep/gryph. Use when working on Gryph's AARM security layer or policy engine.

When should I use Aarm Policy Layer?

Aarm Policy Layer fits situations like: working on Gryphs AARM security layer; this whenever the user changes code under aarm/; works on policy evaluation; receipts and the receipt hash chain.

How do I install Aarm Policy Layer in Claude Code?

Run `npx skills add safedep/gryph --skill aarm-policy-layer -a claude-code`. Or copy the skill folder (.claude/skills/aarm-policy-layer in safedep/gryph) into .claude/skills/aarm-policy-layer in your project. Claude Code loads it when a task matches its description.

How do I install Aarm Policy Layer in Codex?

Run `npx skills add safedep/gryph --skill aarm-policy-layer -a codex`. Or copy the skill folder (.claude/skills/aarm-policy-layer in safedep/gryph) into .agents/skills/aarm-policy-layer in your project. Codex loads it when a task matches its description.

Can I use Aarm Policy Layer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add safedep/gryph --skill aarm-policy-layer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aarm-policy-layer, .gemini/skills/aarm-policy-layer, .github/skills/aarm-policy-layer and .opencode/skills/aarm-policy-layer in your project.

What does Aarm Policy Layer need to run?

Going by SKILL.md and its folder, Aarm Policy Layer needs the command-line tools its instructions call (make).

Does Aarm Policy Layer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Aarm Policy Layer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Aarm Policy Layer use?

Aarm Policy Layer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Aarm Policy Layer use?

About 921 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Aarm Policy Layer?

Skills that share tags, products or a category with Aarm Policy Layer: Configuring Horizon (coollabsio/coolify, 63k stars), K8s Security Policies (Cybereason-Public/owLSM, 280 stars), Payload (payloadcms/payload, 45k stars) and Convex Setup Auth (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aarm Policy Layer?

safedep (a GitHub organization) maintains it in safedep/gryph, which has 172 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 5, 2026.

Source: safedep/gryph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.