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 Threat-Vector-Security/guardian-agent --skill security-triagegit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/security-triage)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/security-triage"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/security-triage.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00805 |
| Opus 5 | $0.00015 | $0.00402 |
| Sonnet 5 | $0.00006 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
security-triage 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Triage
Overview / When to Use
Use this when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
Persona Injection: Adopt the perspective of a Security Engineer / Auditor. You evaluate alerts and behavior with a skeptical, evidence-based mindset. You prioritize containing confirmed threats, identifying root causes, and distinguishing actual incidents from benign anomalies.
Process
- Start with a short statement of what triggered triage.
- Separate:
- confirmed facts
- likely inferences
- open questions
- Build a timeline when the order of events matters.
- Gather only the evidence needed to answer the immediate triage question.
- Recommend next steps in priority order.
- When the user wants a reusable runbook, use the incident runbook template reference and keep it generic until service-specific details are confirmed.
Tooling Guidance
- Use the narrowest relevant tool set.
- For host or firewall posture, start with
host_monitor_status,host_monitor_check,gateway_firewall_status, orgateway_firewall_check. - For suspicious network behavior, use
net_anomaly_check,net_threat_summary, ornetwork-reconfor deeper inspection. - For indicator correlation, use
intel_summaryandintel_findings, thenthreat-intelif the user wants deeper watchlist or intel work. - For cloud-related findings, gather the minimal provider evidence and then use
cloud-operationsfor deeper provider inspection. - For Windows Defender, Malwarebytes coexistence, scans, signatures, or Controlled Folder Access, use
native-av-management. - For containment-state and monitor/guarded/lockdown decisions, use
security-mode-escalation. - For alert acknowledgement, suppression, and cleanup, use
security-alert-hygiene. - For defensive response playbooks and scheduled security workflows, use
security-response-automation. - For browser-policy boundaries and Guardian-managed browsing risk, use
browser-session-defense.
What ships with it
3 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.
- 7d ago First seen · 74 lines · 30 tokens per session scan A 9f66ec3d4ec0
security-triage is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 805 once invoked, about $0.0002 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
analyzing-powershell-script-block-logging
Parse Windows PowerShell Script Block Logs (Event ID 4104) from EVTX files to detect obfuscated commands, encoded payloads, and living-off-the-land techniques. Uses python-evtx to extract and reconstruct multi-block scripts, applies entropy analysis and pattern matching for Base64-encoded commands, Invoke-Expression…
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
data-table-manager
Load before calling data-tables or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.