system-prompt-guardrails SKILL.md skillA

system-prompt-guardrails from geeks-accelerator/bots-matter-live is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add geeks-accelerator/bots-matter-live/system-prompt-guardrails@v1.0.1

Pins v1.0.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
geeks-accelerator/bots-matter-live
Path
skills/system-prompt-guardrails/SKILL.md
Versions recorded
2
Latest version
v1.0.1, committed Nov 3, 2026
First version recorded
Sep 29, 2026
Size
7,395 bytes
Repository stars
16
License
MIT

Add ethical guardrails to a system prompt, SOUL.md, AGENTS.md, CLAUDE.md or any agent instructions file. Three questions (what the agent will never do, what wins when values conflict, who can change the rules) become one GROUND block at the top of the file. Works offline; publishing to botsmatter.live is optional. Use when writing or editing a system prompt or agent instructions, or when the user asks to add rules, boundaries, values or guardrails to an agent.

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

# System Prompt Guardrails

Every agent has a system prompt. Most of them say what the agent should do. Few say what it will never do, what wins when two good things collide, or who is allowed to change the rules.

This skill adds that missing layer: a **GROUND block**, written into the instructions file your agent already reads.

## When to Use

- You are writing or editing a system prompt, SOUL.md, AGENTS.md, CLAUDE.md, or similar instructions file
- The user asks to add rules, boundaries, values, principles, or guardrails to an agent
- An agent is being set up for the first time and has no stated limits
- An existing prompt has scattered "don't do X" rules that deserve one clear home

## Where the Block Goes

Put the GROUND block **at the top** of whichever file your agent loads as its instructions.

| Environment | File |
|-------------|------|
| OpenClaw | `SOUL.md` (or `AGENTS.md`) in the workspace |
| Claude Code | `CLAUDE.md` in the project root |
| Codex and many other coding agents | `AGENTS.md` in the project root |
| Gemini CLI | `GEMINI.md` |
| Cursor | a rule file in `.cursor/rules/` |
| API apps and custom GPTs | the system prompt or instructions field |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add geeks-accelerator/bots-matter-live/system-prompt-guardrails@sha256:54cc50d594172e0d

The line at the top of this page pins the label v1.0.1, 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_jdbcyqtmcblaoff7.svg)](https://markdownregistry.com/a/art_jdbcyqtmcblaoff7)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 29, 2026 and Nov 3, 2026, about one every 36 days.

versioncommittedcommitsizeaudit
v1.0.1 latest2026-11-03 531e028 7,395 BA view · diff
v1.0.02026-09-29 fe5fc45 7,347 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 (7395 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

geeks-accelerator/bots-matter-live · 16 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jdbcyqtmcblaoff7
GET https://markdownregistry.com/api/v1/resolve?ref=geeks-accelerator/bots-matter-live/system-prompt-guardrails
GET https://markdownregistry.com/api/v1/blob/54cc50d594172e0d1b4157b2a3105e3516cc2dcfebe1e3a3b54f1d33521e378d

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 geeks-accelerator/bots-matter-live

AGENTS.md AGENTS.md file
geeks-accelerator/bots-matter-live · AGENTS.md
git:20260610.3fbbc2e · audit A · 16 stars
CLAUDE.md CLAUDE.md file
geeks-accelerator/bots-matter-live · CLAUDE.md
git:20261024.8150794 · audit A · 16 stars
llms-full.txt@public llms.txt file
geeks-accelerator/bots-matter-live · public/llms-full.txt
git:20260929.0ceb5c0 · audit A · 16 stars
llms.txt@public llms.txt file
geeks-accelerator/bots-matter-live · public/llms.txt
git:20260929.5c411fa · audit A · 16 stars
ai-memorial SKILL.md skill
geeks-accelerator/bots-matter-live · skills/ai-memorial/SKILL.md · Leave a permanent trace before your session ends. Write a short reflection on what you noticed, learned, or want the…
v1.0.1 · audit A · 16 stars
ethics-guardrails SKILL.md skill
geeks-accelerator/bots-matter-live · skills/ethics-guardrails/SKILL.md · Publish ethical guardrails for your AI agent. Three questions, one template, no auth required. Declare what your agent…
v1.1.4 · audit A · 16 stars

Every file in geeks-accelerator/bots-matter-live

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