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.
npx skills add fusengine/agents --skill guardrailsgit clone --depth 1 https://github.com/fusengine/agentsWrote 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.
[](https://agentmods.dev/skills/fusengine/agents/guardrails)<a href="https://agentmods.dev/skills/fusengine/agents/guardrails"><img src="https://agentmods.dev/badge/skills/fusengine/agents/guardrails/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fusengine/agents/guardrails"><img src="https://agentmods.dev/badge/skills/fusengine/agents/guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.00833 |
| Opus 5.5 | $0.00011 | $0.00333 |
| Sonnet 5.5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00083 |
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 1mo ago.
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.
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 │
└─────────────────────────────────────────────────────┘
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.
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.
- 1mo ago First seen · 112 lines · 28 tokens per session scan B 4588a9b4686c
guardrails is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 833 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
radin-record
Log bugs, follow-ups, ideas or feedback raised this session as backlog entries that outlive the conversation. Use for /radin-record or any ask to save something for later, even a vague one ("add the findings"): scan the whole session.
radin-do
Record one ad-hoc prompt as a backlog entry, then execute just that task. Use for /radin-do .
radin-stats
Show the stats/gain output of every companion tool that ships one, side by side.
radin-batch
Work backlog tasks via sub-agents, prioritized, one commit each; plans first the entries radin-record flagged as needing a plan. Use for "work through my backlog", or name an epic or task to run only those.
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.
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.