Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vectra-ai-research/vectra-soc-agent-starternpx agentmods add skills/vectra-ai-research/vectra-soc-agent-starter/vectra-investigatorWrote 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/vectra-ai-research/vectra-soc-agent-starter/vectra-investigator)<a href="https://agentmods.dev/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-investigator"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-investigator/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/vectra-ai-research/vectra-soc-agent-starter/vectra-investigator"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-investigator.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 | $0.00189 | $0.04993 |
| Opus 5 | $0.00095 | $0.02497 |
| Sonnet 5 | $0.00038 | $0.00999 |
| Haiku 4.5 | $0.00019 | $0.00499 |
Grade A, and why
vectra-investigator scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl` against `/oauth2/token` and `/investigation/results` is a How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vectra Investigator — Tier 1 SOC Workflow Orchestrator
This is the main orchestration skill for operating Vectra AI (RUX)
as a tier-1 SOC analyst. It owns the full triage layer — which
workflow fits the ask, how to run the matching detection-category
playbook, how to scope across tenants, how to land a verdict. The
detail for each piece lives in references/; load only
what the current context calls for — see
references/MANIFEST.md for the required
per-workflow load set (progressive load is mandatory).
| Sub-area | Reference file |
|---|---|
| The Vectra mental model + multi-tenancy | references/mental-model.md |
| Verdict rubric (BTP / TP-Low / TP-High / NMD) and write-up template | references/verdict-framework.md |
| Detection-category playbook overview (structure + how-to-use + index) | references/playbooks-overview.md |
| Playbook — Exfiltration (Smash and Grab, Hidden Tunnels, Cloud Storage, M365 Download / Mail Forwarding) | references/playbook-exfiltration.md |
| Playbook — Lateral Movement (Suspicious Admin, Kerberoasting, Brute-Force, RPC Recon, LDAP, RDP, Ransomware, Privilege Anomaly) | references/playbook-lateral-movement.md |
| Workflow 1 — Queue Triage | references/workflow-queue-triage.md |
| Workflow 2 — Entity Deep-Dive | references/workflow-entity-deep-dive.md |
| Workflow 3 — Single-Detection Pivot | references/workflow-detection-pivot.md |
| Workflow 4 — TI-Driven Hunt | references/workflow-ti-hunt.md |
| Workflow 5 — Ad-Hoc Investigation Query | references/workflow-ad-hoc-query.md |
| Workflow 6 — Canned Report | references/workflow-canned-report.md |
| Workflow 7 — Network PCAP Triage | references/workflow-pcap-triage.md |
| Best practices + common pitfalls | references/best-practices.md |
The data and SQL detail is delegated to other skills:
- Direct entity / detection lookups → Vectra MCP REST tools (see Direct Vectra MCP lookups below).
- Ad-hoc SQL recipes + TI-driven hunts →
vectra-hunt. - Canned dashboards / KPI reports →
vectra-reports(Python) orvectra-reports-mcp(MCP). - Network detection PCAPs →
vectra-pcap. Cloud / log-based detections (M365, Entra / Azure AD, AWS CloudTrail, …) have no PCAP — those stay on metadata pivots. - External IOC reputation →
virustotal(corroboration only, never overrides the behavioural verdict).
Universal SOC rules (read-only by default, human-in-the-loop for mutations, scope discipline, evidence preservation, output expectations) live in
../../AGENTS.mdand apply to everything below. This file adds the Vectra-specific layer on top.
What ships with it
14 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.
- references/best-practices.md 6.0 KB
- references/MANIFEST.md 2.5 KB
- references/mental-model.md 6.0 KB
- references/playbook-exfiltration.md 17 KB
- references/playbook-lateral-movement.md 23 KB
- references/playbooks-overview.md 6.0 KB
- references/verdict-framework.md 5.5 KB
- references/workflow-ad-hoc-query.md 2.9 KB
- references/workflow-canned-report.md 3.6 KB
- references/workflow-detection-pivot.md 3.6 KB
- references/workflow-entity-deep-dive.md 3.9 KB
- references/workflow-pcap-triage.md 3.4 KB
- references/workflow-queue-triage.md 6.2 KB
- references/workflow-ti-hunt.md 2.9 KB
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.
- 12d ago First seen · 311 lines · 189 tokens per session scan A 3b9ac65497ba
vectra-investigator is a skill published in the GitHub repository vectra-ai-research/vectra-soc-agent-starter (2 stars, last pushed 3d ago), licensed MIT. It adds 189 tokens to every session and 4,993 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…