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:20260928.73c65f9Pins git:20260928.73c65f9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- alelaguard/agentguards-plugins
- Path
codex/skills/guardrails/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260928.73c65f9, committed Sep 28, 2026
- First version recorded
- Jul 2, 2026
- Size
- 2,206 bytes
- Repository stars
- 4
- License
- MIT
How AgentGuards enforces its guardrails in Codex — fully automatic, via hooks, with nothing for you to call. Load this if asked how AgentGuards works, whether you need to screen something yourself, or why no agentguards check_input / authorize_action 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 — enforced by hooks This plugin has no MCP server, so there is no `check_input`, `authorize_action` or `health_check` tool — do not look for them, they are not installed. That is not reduced protection. The hooks in `hooks/hooks.json` enforce deterministically, on every request, whatever the model does: - **`UserPromptSubmit`** screens every prompt before you see it. - **`PreToolUse`** authorizes every shell command before it runs: denied, or allowed, or left to Codex's own approval prompt. For a web fetch (`curl`, `wget`, or a web-fetching MCP tool) it first checks the URLs, and denies a fetch whose URL carries a secret or targets a blocked destination. - **`PermissionRequest`** rides that approval prompt: it denies what AgentGuards rejects and remembers what the user approved for the rest of the session. - **`PostToolUse`** scans the output of shell commands that fetch (`curl`, `wget`, `http`, `fetch`, `aria2c` — also behind `sudo`, `timeout`, `bash -c`, `$(...)`) and of web-fetching MCP tools: instructions hidden in a page are removed and you get the rest with a note; a page with a visible attack, or …
Read the whole file at its exact version.
How to install
mdr add alelaguard/agentguards-plugins/guardrails@sha256:dcc5859f05e8c8b5The line at the top of this page pins the label git:20260928.73c65f9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_avqebz47fsvfpbnj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 2, 2026 and Sep 28, 2026, about one every 29 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260928.73c65f9 latest | 2026-09-28 | 73c65f9 | 2,206 B | A | view · diff |
| git:20260924.03eda53 | 2026-09-24 | 03eda53 | 1,853 B | A | view · diff |
| git:20260702.0fd73be | 2026-07-02 | 0fd73be | 4,653 B | A | view · diff |
| git:20260702.0c35e1f | 2026-07-02 | 0c35e1f | 4,636 B | B | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2206 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
alelaguard/agentguards-plugins · 4 stars · license MIT · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_avqebz47fsvfpbnj GET https://markdownregistry.com/api/v1/resolve?ref=alelaguard/agentguards-plugins/guardrails GET https://markdownregistry.com/api/v1/blob/dcc5859f05e8c8b574303827189642cb3e53516f2eba5cb342bf530987768955
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