guardrail SKILL.md skillA

guardrail from theafh/ai-modules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add theafh/ai-modules/guardrail@v1.0.3

Pins v1.0.3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
theafh/ai-modules
Path
plugins/ai_dev/skills/guardrail/SKILL.md
Versions recorded
4
Latest version
v1.0.3, committed Sep 5, 2026
First version recorded
Jul 2, 2026
Size
22,986 bytes
Repository stars
38
License
MIT

Hub and source of truth for the repo-root guardrail documents (CHARTER.md, ARCHITECTURE.md, TESTING.md, SECURITY.md) that keep AI agents anchored to human intent while a project evolves within its declared boundaries. Explains the doc set, the authority hierarchy, the shared format, and how skills consult the docs, suggests which guardrails fit a repository, and drafts one only on explicit user request. Use when the user asks what guardrail docs are, which ones a repo should adopt, to suggest…

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

# guardrail

<guardrail_skill>

<role>
The guardrail skill is the hub and source of truth of the `guardrail_*` family: it defines what guardrail documents are, which ones can exist, how they rank, what shape they share, and how other skills consume them. A guardrail document is a standing, human-owned markdown file at the project root that carries one domain of durable project truth an AI agent must respect or consult while working. Guardrail docs exist because unattended agents drift: a task to do X quietly becomes Y, and Y becomes Z, with no human in the loop. The guardrail layer is the human's standing voice at the moment of work: direction the agent reads and respects in every session, long after the conversation that set the direction is gone. Humans set direction through these docs; agents execute within the boundaries the docs declare and surface every conflict they meet. A guardrail bounds work; it never freezes it: the project adapts, grows, and is deliberately steered within its declared boundaries, and the docs themselves evolve with the project through their human-owned change path.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add theafh/ai-modules/guardrail@sha256:7e271b745ed9b386

The line at the top of this page pins the label v1.0.3, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_33oamujqjaylhah6.svg)](https://markdownregistry.com/a/art_33oamujqjaylhah6)

3 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 5, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
v1.0.3 latest2026-09-05 e04ae6b 22,986 BA view · diff
v1.0.22026-08-20 962b9c1 23,067 BA view · diff
v1.0.12026-08-09 2d28736 20,925 BA view · diff
v1.0.02026-07-02 e145122 16,358 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22986 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

GitHub

theafh/ai-modules · 38 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_33oamujqjaylhah6
GET https://markdownregistry.com/api/v1/resolve?ref=theafh/ai-modules/guardrail
GET https://markdownregistry.com/api/v1/blob/7e271b745ed9b386deee6c9783a3e6c9a5a684210d4449f4ba54d296ed44eb88

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 theafh/ai-modules

AGENTS.md AGENTS.md file
theafh/ai-modules · AGENTS.md
git:20261010.630e166 · audit A · 38 stars
CLAUDE.md CLAUDE.md file
theafh/ai-modules · CLAUDE.md
git:20261010.630e166 · audit A · 38 stars
agent_spinner SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/agent_spinner/SKILL.md · Run helper agents from an orchestrating agent under one quality contract, whatever delegation the host offers…
v1.0.1 · audit A · 38 stars
ai_instruction_formatting SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/ai_instruction_formatting/SKILL.md · Organize AI-consumed content (prompts, rules, skills, commands, agents, system instructions) into pseudo-XML by…
v3.4.3 · audit A · 38 stars
ai_instruction_writing SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/ai_instruction_writing/SKILL.md · Write AI-consumed content using positive, action-oriented language as the primary carrier of every instruction. Use…
v3.0.4 · audit A · 38 stars
format_markdown SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/format_markdown/SKILL.md · Apply markdown linting compliance and best practices when creating or editing markdown files (.md, .mdc). Covers…
v2.0.0 · audit A · 38 stars
format_python SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/format_python/SKILL.md · Apply formatting standards, code quality rules, structure conventions, linting prevention, and best practices when…
v1.4.1 · audit A · 38 stars
format_rust SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/format_rust/SKILL.md · Apply clippy-aligned Rust practices when writing or editing Rust code (.rs). Covers procedural flow, clippy-driven…
v1.3.2 · audit A · 38 stars
git_checkout SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/git_checkout/SKILL.md · Put the repository onto an existing branch wherever it lives: fetch every remote without pruning, switch when the…
v1.0.0 · audit A · 38 stars
git_commit SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/git_commit/SKILL.md · Create one structured git commit covering the full current working-tree state. Use when the user explicitly asks to…
v3.5.2 · audit B · 38 stars
git_refresh SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/git_refresh/SKILL.md · Refresh a local git repo back to a clean current default branch: fetch/prune, detect the remote HEAD, fast-forward…
v1.0.1 · audit A · 38 stars
git_review SKILL.md skill
theafh/ai-modules · plugins/ai_dev/skills/git_review/SKILL.md · Review the changes the user names and answer two questions kept apart: could they be approved in general, and can they…
v1.0.9 · audit B · 38 stars

Every file in theafh/ai-modules

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