guardrails SKILL.md skillA

guardrails from fusengine/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add fusengine/agents/guardrails@git:20260729.3b91eed

Pins git:20260729.3b91eed in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
fusengine/agents
Path
plugins/prompt-engineer/skills/guardrails/SKILL.md
Versions recorded
5
Latest version
git:20260729.3b91eed, committed Jul 29, 2026
First version recorded
Jan 22, 2026
Size
5,196 bytes
Repository stars
36
License
MIT

Use when implementing input/output guardrails, writing ethical guardrail templates, or auditing an agent/prompt for missing security controls.

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

<objective>
Guardrails covers the 4-layer security architecture for an agent or prompt: input (harmlessness screening, jailbreak pattern matching, PII redaction), system (ethical guardrails in the system prompt, explicit capability limits, refusal instructions), output (format validation, hallucination detection, compliance checks), and monitoring (interaction logs, suspicious-pattern alerts, rate limiting).

It includes a ready-to-use ethical-guardrails template and a security checklist covering both the agent level (guardrails per layer, least-privilege tools, logging) and the prompt level (explicit Forbidden section, capability limits, error-case handling, no hardcoded sensitive data).
</objective>

# Guardrails

Skill for implementing security guardrails and quality control.

## 4-Layer Security Architecture

```
┌─────────────────────────────────────────────────────┐
│                 LAYER 1: Input                       │
│ - Harmlessness screen (lightweight LLM)             │
│ - Pattern matching (jailbreak regex)                │
│ - PII detection/redaction                           │
└─────────────────────────────────────────────────────┘
                         │
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add fusengine/agents/guardrails@sha256:4588a9b4686c36bc

The line at the top of this page pins the label git:20260729.3b91eed, 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_nqy36mtfdizdwivq.svg)](https://markdownregistry.com/a/art_nqy36mtfdizdwivq)

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

Versions

The registry has recorded 5 versions of this file, between Jan 22, 2026 and Jul 29, 2026, about one every 47 days. Its first recorded version is graded C and its latest A.

versioncommittedcommitsizeaudit
git:20260729.3b91eed latest2026-07-29 3b91eed 5,196 BA view · diff
git:20260705.ba8ee522026-07-05 ba8ee52 4,549 BA view · diff
git:20260705.8c2f9bc2026-07-05 8c2f9bc 4,547 BA view · diff
git:20260124.acdc9412026-01-24 acdc941 4,402 BA view · diff
git:20260122.f6bc08c2026-01-22 f6bc08c 7,688 BC 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 (5196 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

fusengine/agents · 36 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nqy36mtfdizdwivq
GET https://markdownregistry.com/api/v1/resolve?ref=fusengine/agents/guardrails
GET https://markdownregistry.com/api/v1/blob/4588a9b4686c36bc6e5bf944f3f0601e6b17763aa1d559d1185b46da3c66ef03

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 fusengine/agents

agent-creator SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/agent-creator/SKILL.md · Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
git:20260904.5f1d30f · audit A · 36 stars
apex-methodology SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/apex-methodology/SKILL.md · Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix…
git:20261012.499a4d1 · audit A · 36 stars
brainstorming SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/brainstorming/SKILL.md · Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via…
git:20260904.5f1d30f · audit A · 36 stars
challenge SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/challenge/SKILL.md · Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain…
git:20260729.3b91eed · audit A · 36 stars
code-quality SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/code-quality/SKILL.md · Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture…
git:20261012.499a4d1 · audit A · 36 stars
elicitation SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/elicitation/SKILL.md · Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation…
git:20260729.3b91eed · audit A · 36 stars
exploration SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/exploration/SKILL.md · Use when exploring an unfamiliar codebase -- architecture analysis, pattern detection, dependency mapping, rapid…
git:20260729.3b91eed · audit A · 36 stars
fuse-browser-usage SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/fuse-browser-usage/SKILL.md · Use when about to call any mcp__fuse-browser__* tool. Routes fetch/crawl/SERP vs live browser session vs screenshot…
git:20260729.3b91eed · audit A · 36 stars
lead-orchestration SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/lead-orchestration/SKILL.md · Use when you are the LEAD (main session) and an owner request arrives that needs agents -- intake, routing, briefs…
git:20261012.f15b04e · audit A · 36 stars
modularize SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/modularize/SKILL.md · Use when converting existing code to modular architecture (Laravel, Next.js, React). Triggers: "modularize", "convert…
git:20260729.3b91eed · audit A · 36 stars
pr-summary SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/pr-summary/SKILL.md · Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.
git:20260729.3b91eed · audit A · 36 stars
react-effects-audit SKILL.md skill
fusengine/agents · plugins/ai-pilot/skills/react-effects-audit/SKILL.md · Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from…
git:20260729.3b91eed · audit A · 36 stars

Every file in fusengine/agents

Other files named guardrails

guardrails SKILL.md skill
ai-analyst-lab/ai-analyst · .claude/skills/guardrails/SKILL.md · Ensure every success metric is paired with guardrail metrics and check for trade-offs before presenting improvements as…
git:20260827.7ff2e25 · audit A · 322 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · claude/skills/guardrails/SKILL.md · How AgentGuards enforces its guardrails in Claude Code — fully automatic, via hooks, with nothing for you to call. Load…
git:20260924.03eda53 · audit A · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · codex/skills/guardrails/SKILL.md · How AgentGuards enforces its guardrails in Codex — fully automatic, via hooks, with nothing for you to call. Load this…
git:20260928.73c65f9 · audit A · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · codex-selfhosted/skills/guardrails/SKILL.md · AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks…
git:20260804.c8a22f2 · audit A · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · gemini-selfhosted/skills/guardrails/SKILL.md · AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks…
git:20260804.c8a22f2 · audit A · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · opencode/skills/guardrails/SKILL.md · AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking…
git:20260713.7345168 · audit B · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · gemini/skills/guardrails/SKILL.md · AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking…
git:20261006.fcf182e · audit A · 4 stars
guardrails SKILL.md skill
alelaguard/agentguards-plugins · claude-selfhosted/skills/guardrails/SKILL.md · AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks…
git:20260804.4143397 · audit B · 4 stars

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