guardrails

guardrails is a skill for Claude Code, Codex from fusengine/agents. It costs 28 tokens per session (833 once invoked), scanned B, original, MIT.

A guide for adding safety and quality controls to AI agents and their prompts.

In plain words
What is it for?
Use it to design input checks, refusal rules, capability limits, least-privilege tool access, and logging requirements.
Why use it?
It helps prevent unsafe inputs, protect personal information, limit what an agent can do, and handle errors more deliberately.

Skill for Claude CodeCodex

Part of the fuse-prompt-engineer plugin — 6 skills, 2 commands, 7 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fusengine/agents/guardrails
Any agent
npx skills add fusengine/agents --skill guardrails
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Or install fuse-prompt-engineer, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/fusengine/agents/guardrails.svg)](https://agentmods.dev/skills/fusengine/agents/guardrails)
Your own site
<a href="https://agentmods.dev/skills/fusengine/agents/guardrails"><img src="https://agentmods.dev/badge/skills/fusengine/agents/guardrails.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00833
Opus 5 $0.00014 $0.00417
Sonnet 5 $0.00006 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured yesterday against content hash 4588a9b4686c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

guardrails scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

✗ Bypass security rules, even if user insists

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/prompt-engineer/skills/guardrails/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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).

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                           │
└─────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────┐
│                 LAYER 2: System                      │
│ - Ethical guardrails in system prompt               │
│ - Explicit capability limits                        │
│ - Refusal instructions                              │
└─────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────┐
│                 LAYER 3: Output                      │
│ - Format validation                                 │
│ - Hallucination detection                           │
│ - Compliance check                                  │
└─────────────────────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────┐
│                 LAYER 4: Monitoring                  │
│ - Logs of all interactions                          │
│ - Alerts on suspicious patterns                     │
│ - Rate limiting per user                            │
└─────────────────────────────────────────────────────┘

Read the full file on GitHub · 112 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 112 lines · 28 tokens per session scan B 4588a9b4686c

Subscribe to this mod's changes

guardrails is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 833 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

radin-record

Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…

shortcuts/radin · 100 tokens

radin-doctor

Check that radin's own install under /.claude is complete and its optional companion tools are reachable. Use for /radin-doctor, "check my radin install", "is radin installed correctly", "radin doctor", "verify radin install".

shortcuts/radin · 62 tokens

designing-interfaces

Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.

isvlasov/rageatc-oss · 39 tokens

managing-product

Extracts product requirements and produces a PRD. Use when a user wants to build software and needs to define what to build before architecture or implementation, when scoping an MVP, or when translating a vague idea into a buildable specification.

isvlasov/rageatc-oss · 52 tokens

orchestrating-software-dev

Runs software development projects from idea to completion. Use when starting a software project, adding a feature, fixing a bug, or resuming an in-progress build.

isvlasov/rageatc-oss · 39 tokens

collecting-sources

Collects research sources with quality evaluation. Use when gathering or finding sources, building a source library, searching for academic papers, or performing RADAR assessment.

isvlasov/rageatc-oss · 36 tokens