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 dandye/ai-runbooks --skill hunt-threatgit clone --depth 1 https://github.com/dandye/ai-runbooksWrote 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/dandye/ai-runbooks/hunt-threat)<a href="https://agentmods.dev/skills/dandye/ai-runbooks/hunt-threat"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/hunt-threat/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/dandye/ai-runbooks/hunt-threat"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/hunt-threat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 20 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00049 | $0.01394 |
| Opus 5 | $0.00024 | $0.00697 |
| Sonnet 5 | $0.00010 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
hunt-threat 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 13d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advanced Threat Hunting Skill
Conduct proactive, hypothesis-driven threat hunts based on threat intelligence, observed anomalies, or specific TTPs.
Inputs
HUNT_HYPOTHESIS- Clear statement of the hunt objective (required)- Example: "Suspected DNS tunneling for C2 based on recent actor TTPs"
- Example: "Anomalous PowerShell execution on critical servers"
- Example: "Living-off-the-land techniques bypassing EDR"
- (Optional)
RELEVANT_GTI_REPORTS- GTI Collection IDs or report names - (Optional)
TARGET_SCOPE_QUERY- UDM query to narrow initial scope TIME_FRAME_HOURS- Lookback period (default: 168 = 7 days)- (Optional)
HUNT_CASE_ID- case for tracking the hunt
Workflow
Step 1: Define Hypothesis & Scope
Clearly articulate:
- What threat behavior are we looking for?
- What would evidence of this look like in logs?
- What systems/users are in scope?
- What time period is relevant?
Create or identify HUNT_CASE_ID for documentation.
Step 2: Deep Intelligence Analysis
For each relevant GTI report:
gti-mcp.get_collection_report(id=REPORT_ID)
gti-mcp.get_entities_related_to_a_collection(id=REPORT_ID, relationship_name="attack_techniques")
gti-mcp.get_collection_timeline_events(id=REPORT_ID)
gti-mcp.get_collection_mitre_tree(id=REPORT_ID)
Also:
gti-mcp.get_threat_intel(query="Details on specific TTPs")
Step 3: Develop Initial Hunt Queries
Based on hypothesis and intelligence, formulate advanced queries:
SIEM queries:
secops-mcp.search_security_events(
text="Advanced UDM query targeting specific behaviors",
hours_back=TIME_FRAME_HOURS
)
BigQuery (for large-scale analysis):
bigquery.execute-query(query="Complex analytical query")
Step 4: Iterative Search & Analysis
Hunt Loop:
- Execute queries
- Analyze results for outliers, suspicious patterns
- Identify leads (suspicious hosts, users, processes, connections)
- Refine hypothesis based on findings
- Develop new, more targeted queries
- Repeat until exhausted or time limit reached
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.
- 13d ago First seen · 192 lines · 49 tokens per session scan A b43d07200604
hunt-threat is a skill published in the GitHub repository dandye/ai-runbooks (126 stars, last pushed 28d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,394 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
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…