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-huntWrote 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-hunt)<a href="https://agentmods.dev/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-hunt"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-hunt/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-hunt"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/vectra-hunt.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 | $0.00214 | $0.02976 |
| Opus 5 | $0.00107 | $0.01488 |
| Sonnet 5 | $0.00043 | $0.00595 |
| Haiku 4.5 | $0.00021 | $0.00298 |
Grade A, and why
vectra-hunt 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 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.
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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vectra Hunt — Metadata Search & Threat-Intel Hunting
This skill is the search and hunt layer over Vectra metadata. It runs in two modes:
| Mode | Trigger | Output | Reference |
|---|---|---|---|
| Ad-hoc query | "Did host X talk to evil.com last night?", "Find RC4 TGS requests", "Show me POST exfil traffic" | Single Investigation Query result, summarized in chat | references/mode-ad-hoc.md |
| TI-driven hunt | "Hunt this CISA advisory", "Sweep our tenant for APT-9999", "Are we affected by this Cobalt Strike campaign?" | Multi-query sweep + consolidated hunt report (IOC hits, TTP coverage, gaps, recommendations) | references/mode-ti-hunt.md |
Both modes draw on the same library of pre-validated SQL recipes (catalog below). Ad-hoc mode runs one recipe. TI mode batches many of them around a report's IOCs and TTPs.
This is not:
- A canned dashboard / KPI report — that's
vectra-reports(Python) orvectra-reports-mcp(MCP). - A detection-triage playbook ("how do I triage a Smash and Grab?")
or queue-triage workflow ("walk me through tier 1") — that's
vectra-investigator(loads the matchingplaybook-<category>.md).
How this skill is organized
The detail for each piece lives in references/ —
load only what the current task needs (see
references/MANIFEST.md for the required
per-mode and per-domain load set; progressive load is mandatory).
Two distinct kinds of reference file:
Orchestration / methodology (how to run the skill):
| Sub-area | Reference |
|---|---|
| Mode 1 — Ad-hoc workflow + decision guide | references/mode-ad-hoc.md |
| Mode 2 — TI-hunt 6-phase methodology + execution rules | references/mode-ti-hunt.md |
| MITRE TTP & tools/malware → recipe lookup (used by both modes) | references/ti-hunt-ttp-map.md |
| TI Hunt Report markdown template (Phase 6 of TI-hunt) | references/ti-hunt-report-template.md |
| Query Construction Rules (SQL — used when no recipe matches) | references/query-construction.md |
| Table-specific gotchas (per-table quirks to check before authoring) | references/table-gotchas.md |
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.
- examples.md 13 KB
- references/cloud_investigations.md 13 KB
- references/MANIFEST.md 2.0 KB
- references/mode-ad-hoc.md 3.3 KB
- references/mode-ti-hunt.md 6.8 KB
- references/network_dns_http.md 4.3 KB
- references/network_infra.md 10 KB
- references/network_lateral_movement.md 12 KB
- references/network_sessions.md 3.7 KB
- references/network_tls_certs.md 5.1 KB
- references/query-construction.md 3.6 KB
- references/table-gotchas.md 1.9 KB
- references/ti-hunt-report-template.md 3.1 KB
- references/ti-hunt-ttp-map.md 4.4 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 · 204 lines · 214 tokens per session scan A 0c2ee48c4073
vectra-hunt 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 214 tokens to every session and 2,976 once invoked, about $0.0011 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.
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…