guardrails SKILL.md skillA

guardrails from alelaguard/agentguards-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add alelaguard/agentguards-plugins/guardrails@git:20260804.c8a22f2

Pins git:20260804.c8a22f2 in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

alelaguard/agentguards-plugins

Path

gemini-selfhosted/skills/guardrails/SKILL.md

Versions recorded

1

Latest version

git:20260804.c8a22f2, committed Aug 4, 2026

Size

1,849 bytes

Repository stars

4

License

MIT

AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks and there is nothing further to call. Load this if asked how guardrails are enforced in this variant, or why no agentguards MCP tools are available.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AgentGuards — self-hosted, hooks-only

This variant bundles no MCP server, so there is no `check_input`/`authorize_action`
to reach for — do not look for them, they are not installed here.

That is not reduced protection. The three hooks in `hooks/hooks.json` enforce
deterministically, on every request, regardless of anything the model does:

- **`BeforeAgent`** screens every prompt before you see it.
- **`BeforeTool`** authorizes every tool call before it runs.
- **`AfterTool`** scans content fetched by `web_fetch`/`google_web_search`, and
  by `run_shell_command` when it invokes a fetch binary (curl, wget, etc.) —
  withholding it if flagged.

Nothing here requires you to call a tool, check a decision, or format a block
message — the hook has already acted by the time you see (or don't see) the
result. If a hook blocks something, reply with its message rather than
composing your own.

**Why no MCP server:** Gemini CLI's extension manifest cannot substitute an
environment variable into its MCP server URL, so a URL baked in at publish
time cannot be made to point at each installer's own appliance — it would
…

Read the whole file at its exact version.

How to install

mdr add alelaguard/agentguards-plugins/guardrails@sha256:59c8c2d9006bd119

[![mdr](https://markdownregistry.com/badge/art_i2kexmfb54cip6qp.svg)](https://markdownregistry.com/a/art_i2kexmfb54cip6qp)

Versions

The registry has recorded 1 version of this file, committed on Aug 4, 2026.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_i2kexmfb54cip6qp
GET https://markdownregistry.com/api/v1/resolve?ref=alelaguard/agentguards-plugins/guardrails
GET https://markdownregistry.com/api/v1/blob/59c8c2d9006bd119a51854064c806245db04e6df16f780f1fef0b9378afa7f34

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from alelaguard/agentguards-plugins

Every file in alelaguard/agentguards-plugins

Other files named guardrails

Browse by kind, by grade A, or by owner.