ai-guardian

ai-guardian is a skill for Claude Code from AIops-tools/AI-Guardian. It costs 419 tokens per session (4,005 once invoked), scanned A, original, MIT.

A monitoring and governance skill for local language models running on Ollama, llama.cpp, LM Studio, or a single-node vLLM. It inventories models, checks their state and capabilities, and can inspect or govern prompts sent through supported routes.

In plain words
What is it for?
Use it to audit installed or running models, inspect memory use and model details, record local activity, or route prompts through policy checks before calling Ollama.
Why use it?
It provides a record of local model activity and helps control what prompts are sent, including models that may be running without formal approval.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Part of the ai-guardian plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to audit installed or running models, inspect memory use and model details, record local activity, or route prompts through policy checks before calling Ollama.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiops-tools/ai-guardian/ai-guardian
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.

Any agent
npx skills add AIops-tools/AI-Guardian --skill ai-guardian
Clone the repo
git clone --depth 1 https://github.com/AIops-tools/AI-Guardian

Made for: Claude Code.

Or install ai-guardian, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 ai-guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiops-tools/ai-guardian/ai-guardian/github.svg)](https://agentmods.dev/skills/aiops-tools/ai-guardian/ai-guardian)
Your own site
<a href="https://agentmods.dev/skills/aiops-tools/ai-guardian/ai-guardian"><img src="https://agentmods.dev/badge/skills/aiops-tools/ai-guardian/ai-guardian/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.

agentmods 80×15 button for ai-guardian

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiops-tools/ai-guardian/ai-guardian"><img src="https://agentmods.dev/badge/skills/aiops-tools/ai-guardian/ai-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 419 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,005 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00419 $0.04005
Opus 5 $0.00210 $0.02003
Sonnet 5 $0.00084 $0.00801
Haiku 4.5 $0.00042 $0.00400

Measured 10d ago against content hash 2fa412b5f1b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-guardian 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 10d 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.

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.

skills/ai-guardian/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Guardian

Disclaimer: Community-maintained open-source project, not affiliated with, endorsed by, or sponsored by Ollama, IGEL, or any AI-security vendor. Product and trademark names belong to their owners. Source at github.com/AIops-tools/AI-Guardian under the MIT license.

Governed observability + governance for on-endpoint local LLMs (Ollama)21 MCP tools, every one wrapped with the bundled @governed_tool harness: a local unified audit log under ~/.ai-guardian/, token/runaway budget guard, undo-token recording, and descriptive risk tiers. It is the complement to IGEL AI Armor: AI Armor governs whether a local model may run; ai-guardian records what it did and gates what leaves in the prompt.

Ollama keeps no queryable prompt history (context is client-supplied each request), so ai-guardian observes on two fronts: passive inventory / state auditing over /api/tags, /api/ps, /api/show, /api/version; and opt-in route-through content governance — a caller sends a prompt through guarded_generate / observe_chat, which scans + policy-gates + records it and only then calls Ollama.

Standalone: the governance harness is bundled in the package (ai_guardian.governance) — no external skill-family dependency. A transparent capture proxy for other clients' traffic is v0.2 roadmap, and IGEL AI Armor interop is doc-level positioning.

What This Skill Does

Group Tools Count Read/Write
Inventory / state list_models, running_models, model_details, server_status, vram_usage 5 read
Policy / provenance policy_view, model_provenance 2 read
Content governance (read) scan_prompt, usage_events, anomaly_report 3 read
Model lifecycle pull_model (medium), remove_model (high), unload_model (medium) 3 write
Policy writes set_model_allowlist, set_model_denylist, pin_model_digest (all medium) 3 write
Route-through guard guarded_generate, observe_chat (medium) 2 write
Undo undo_list, undo_apply 2 undo

Read the full file on GitHub · 206 lines

Files

What ships with it

4 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. 10d ago First seen · 206 lines · 419 tokens per session scan A 2fa412b5f1b3

Subscribe to this mod's changes

ai-guardian is a skill published in the GitHub repository AIops-tools/AI-Guardian (0 stars, last pushed 8d ago), licensed MIT. It adds 419 tokens to every session and 4,005 once invoked, about $0.0021 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 2026-08-31.

Related

Other skills, from other repositories

inference-aiops

Use this skill whenever the user needs to operate a GPU inference cluster — vLLM (OpenAI API + Prometheus /metrics) and Ray Serve / Ray Jobs (Ray dashboard), plus the single-process serving engines SGLang and TGI (Text Generation Inference): a one-shot cluster overview (deployments + total replicas + queue…

AIops-tools/Inference-AIops · 417 tokens

monitoring-aiops

Use this skill whenever the user needs to operate a network / infrastructure monitoring NOC on SolarWinds Orion (SWIS REST + SWQL), Paessler PRTG (web API), or Zabbix 6.x/7.x (JSON-RPC) — a one-shot NOC overview, canned SWQL answers (nodes down, flapping interfaces, muted, high-CPU nodes, full volumes…

AIops-tools/Monitoring-AIops · 459 tokens

ceph-aiops

Use this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTHWARN/ERR state into cause + action (clusterhealth), read the cluster status, inspect OSDs (tree/df/perf), placement groups (summary/stuck/scrub), pools (list/usable capacity), RBD images…

AIops-tools/Ceph-AIops · 391 tokens

compliance-aiops

Use this skill whenever the user needs compliance evidence from the audit trails their governed AIops agents already write — mapping AI-agent infra-ops activity to HIPAA §164.312, PCI-DSS v4.0, SOC 2 TSC, or GDPR controls, producing a change-approval report, a gap analysis, an exceptions/anomaly report, or a…

AIops-tools/Compliance-AIops · 256 tokens

nutanix-aiops

Use this skill whenever the user needs to operate a Nutanix estate through Prism Central (v4 REST API) — an estate/cluster health overview, cluster & host inventory and utilization, VM lifecycle across AHV and ESXi (list/get/power/create/update/clone/delete/migrate), storage containers, subnets/network, images &…

AIops-tools/Nutanix-AIops · 330 tokens

endpoint-aiops

Use this skill whenever the user needs to operate a managed-endpoint fleet (thin clients, VDI endpoints, centrally-managed devices) — a one-shot fleet health overview, endpoint inventory (list/get), a composite per-endpoint health score (which endpoints are worst?), login & boot sessions, login-storm analysis (detect…

AIops-tools/Endpoint-AIops · 299 tokens