Borrowing it
Nothing to install: this file belongs to yaalalabs/agent-kernel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yaalalabs/agent-kernel/develop/.agents/skills/ak-dev-new-guardrail-provider/SKILL.mdgit clone --depth 1 https://github.com/yaalalabs/agent-kernelWrote 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/yaalalabs/agent-kernel/ak-dev-new-guardrail-provider)<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-guardrail-provider"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-guardrail-provider/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/yaalalabs/agent-kernel/ak-dev-new-guardrail-provider"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-guardrail-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.03213 |
| Opus 5 | $0.00036 | $0.01606 |
| Sonnet 5 | $0.00015 | $0.00643 |
| Haiku 4.5 | $0.00007 | $0.00321 |
Grade A, and why
ak-dev-new-guardrail-provider scanned grade A with 0 findings 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a New Guardrail Provider
This guide walks through adding a new guardrail provider to Agent Kernel. Use the existing OpenAI (ak-py/src/agentkernel/guardrail/openai.py), Bedrock (ak-py/src/agentkernel/guardrail/bedrock.py), and Walled AI (ak-py/src/agentkernel/guardrail/walledai.py) implementations as reference.
Existing Providers
| Provider | Type value | Features | Extra |
|---|---|---|---|
| OpenAI | openai |
Content moderation, jailbreak detection, PII detection (via config JSON) | agentkernel[openai] |
| AWS Bedrock | bedrock |
AWS-managed guardrails (ID + version) | agentkernel[aws] |
| Walled AI | walledai |
Content safety + PII redaction/unmasking (via pii flag) |
agentkernel[walledai] |
Architecture Overview
Agent Kernel's guardrail system uses the hook mechanism:
- Input guardrails subclass the no-op
InputGuardrailclass inguardrail/guardrail.py(itself aPreHook) — they inspect incoming requests and can halt execution by returning anAgentReplyinstead of passing through - Output guardrails subclass the no-op
OutputGuardrailclass (itself aPostHook) — they inspect agent replies and can modify or replace the response BaseGuardrailUtil(also inguardrail/guardrail.py) provides shared text-extraction helpers and is mixed into concrete guardrail classes- Factories in
guardrail.pyselect the appropriate provider based onAKConfig.guardrailconfiguration; unknown types raise an exception, and the no-op classes are returned only when guardrails are disabled - Guardrails are registered as system hooks in
Runtime, meaning they apply to all agents automatically
Step-by-Step
1. Create the Guardrail Provider File
Create ak-py/src/agentkernel/guardrail/<provider>.py.
2. Implement the Base Provider Class
The base class is a plain provider-specific class that holds shared client/config setup. The concrete input/output classes (steps 3 and 4) combine it with the no-op InputGuardrail/OutputGuardrail hooks and the BaseGuardrailUtil mixin. Real examples: class OpenAIInputGuardrail(BaseGuardrailUtil, BaseOpenAIGuardrail, InputGuardrail) in openai.py, class BedrockInputGuardrail(BaseGuardrailUtil, BaseBedrockGuardrail, InputGuardrail) in bedrock.py, and class WalledAIInputGuardrail(InputGuardrail, WalledAIGuardrailBase) in walledai.py.
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.
- today Changed · +2 lines 6b174b4b7de7
- 2d ago Changed b405de865a47
- 9d ago First seen · 302 lines · 73 tokens per session scan A 149a12506756
ak-dev-new-guardrail-provider is a skill published in the GitHub repository yaalalabs/agent-kernel (166 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 3,213 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
notion
Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.
datadog
Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations.
scaleway
Scaleway cloud integration for managing instances, Kapsule Kubernetes clusters, object storage, and managed databases via CLI and Terraform.
isaac-automator
Deploy and operate a cloud Isaac Workstation with Isaac Automator: provision a GPU VM running Isaac Sim, Isaac Lab, and/or Isaac Lab Arena on AWS, GCP, Azure, or Alibaba Cloud, connect to it, move data in and out, control cost with stop/start, repair, import existing deployments, and destroy. Use when the user wants a…
bitbucket
Bitbucket code repository integration for managing repos, branches, PRs, issues, and CI/CD pipelines.
cloudflare
Cloudflare integration for DNS, CDN, WAF, edge diagnostics, and remediation with zone management, analytics, security events, and cache control.