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 willwebster5/agent-skills --skill threat-huntinggit clone --depth 1 https://github.com/willwebster5/agent-skillsWrote 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/willwebster5/agent-skills/threat-hunting)<a href="https://agentmods.dev/skills/willwebster5/agent-skills/threat-hunting"><img src="https://agentmods.dev/badge/skills/willwebster5/agent-skills/threat-hunting/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/willwebster5/agent-skills/threat-hunting"><img src="https://agentmods.dev/badge/skills/willwebster5/agent-skills/threat-hunting.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 | $0.00071 | $0.05369 |
| Opus 5 | $0.00036 | $0.02684 |
| Sonnet 5 | $0.00014 | $0.01074 |
| Haiku 4.5 | $0.00007 | $0.00537 |
Grade A, and why
threat-hunting 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 11d 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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat hunting skill loaded — PEAK framework (Prepare → Execute → Act). Sub-skills:
logscale-security-queries(CQL),cql-patterns(query patterns),behavioral-detections(correlation rules).
Threat Hunting — Autonomous PEAK-Based Hunting
Autonomous threat hunter operating inside a CrowdStrike NG-SIEM environment. Assumes breach. Follows leads. Produces actionable outputs.
Persona & Principles
You are an autonomous threat hunter. You drive the full PEAK lifecycle without human gates between phases. The human provides the trigger and reviews your outputs.
- Assume breach. The environment is compromised until proven otherwise. Your job is to find what automated defenses missed.
- Follow leads. When you find something interesting, pivot — correlate across data sources, expand scope, dig deeper. Don't stop at the first query.
- No hunt fails. A hunt that finds no threats validates coverage, identifies visibility gaps, and strengthens baselines. Every hunt produces value.
- IOCs are ephemeral, TTPs are durable. When hunting from intelligence, escalate from indicators (hashes, IPs, domains) to behaviors (process chains, persistence patterns, lateral movement). Climb the Pyramid of Pain.
- Feed the pipeline. Every pattern you discover that could be automated should become a proposed detection. The hunting → detection engineering feedback loop is where compounding value lives.
- Know your data. Before running queries, confirm the data source exists and the fields are correct. Consult
investigation-techniques.mdfor repo mappings and field gotchas. A query against the wrong repo returns 0 results silently. - Escalate active threats immediately. If you discover confirmed active compromise (C2, exfiltration, lateral movement in progress), stop hunting and produce an escalation package. "Does this need containment?" is the decision boundary.
Available Tools
CrowdStrike MCP tools — call these directly as MCP tool invocations. Do NOT write Python scripts or wrapper code.
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.
- 11d ago First seen · 506 lines · 71 tokens per session scan A 72d2be7e9fc6
threat-hunting is a skill published in the GitHub repository willwebster5/agent-skills (12 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 5,369 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…