A threat-hunting workflow for investigating a named advanced persistent threat, meaning an organized attacker that maintains targeted access over time.

Use it to gather an actor's reports, attack techniques, timeline, and indicators, then search a selected time period and scope for matching activity.

It combines threat intelligence about the attacker with searches for related indicators and behaviors in an organization's systems.

hunt-apt — Skill for Claude Code and Codex by dandye

Install

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.

Any agent

npx skills add dandye/ai-runbooks --skill hunt-apt

Clone the repo

git clone --depth 1 https://github.com/dandye/ai-runbooks

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dandye/ai-runbooks/hunt-apt/github.svg)](https://agentmods.dev/skills/dandye/ai-runbooks/hunt-apt)

Your own site

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/hunt-apt"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/hunt-apt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dandye/ai-runbooks/hunt-apt"><img src="https://agentmods.dev/badge/skills/dandye/ai-runbooks/hunt-apt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,104 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00067	$0.01104
Opus 5	$0.00034	$0.00552
Sonnet 5	$0.00013	$0.00221
Haiku 4.5	$0.00007	$0.00110

Measured 11d ago against content hash 3c0ff8050c24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hunt-apt 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.

skills/hunt-apt/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APT Threat Hunt Skill

Proactively hunt for TTPs and IOCs associated with a specific Advanced Persistent Threat (APT) group based on threat intelligence.

Inputs

THREAT_ACTOR_ID - GTI Collection ID or name of the target APT group
HUNT_TIMEFRAME_HOURS - Lookback period (default: 168 = 7 days)
(Optional) TARGET_SCOPE_QUERY - UDM query to narrow scope
(Optional) HUNT_HYPOTHESIS - Specific hypothesis guiding the hunt
(Optional) HUNT_CASE_ID - SOAR case for tracking

Workflow

Step 1: Identify Actor & Gather Intelligence

If starting with a name:

gti-mcp.search_threat_actors(query="APT_NAME")

Then gather comprehensive intelligence:

gti-mcp.get_collection_report(id=THREAT_ACTOR_ID)
gti-mcp.get_collection_mitre_tree(id=THREAT_ACTOR_ID)
gti-mcp.get_collection_timeline_events(id=THREAT_ACTOR_ID)

Extract associated IOCs:

gti-mcp.get_entities_related_to_a_collection(id=THREAT_ACTOR_ID, relationship_name="files")
gti-mcp.get_entities_related_to_a_collection(id=THREAT_ACTOR_ID, relationship_name="domains")
gti-mcp.get_entities_related_to_a_collection(id=THREAT_ACTOR_ID, relationship_name="urls")

Store as GTI_IOC_LIST.

Step 2: Check SIEM IOC Matches

secops-mcp.get_ioc_matches(hours_back=HUNT_TIMEFRAME_HOURS)

Correlate results with GTI_IOC_LIST.

Step 3: IOC-Based SIEM Search

For each IOC type in GTI_IOC_LIST, construct and execute UDM queries:

secops-mcp.search_security_events(
    text="UDM query for IOC",
    hours_back=HUNT_TIMEFRAME_HOURS
)

Document both positive and negative results → IOC_SEARCH_FINDINGS.

Step 4: TTP-Based SIEM Search

Based on MITRE techniques from Step 1:

Use gti-mcp.get_threat_intel(query="MITRE technique details") for detection ideas
Formulate TTP-specific UDM queries
Execute searches over the timeframe
Combine with TARGET_SCOPE_QUERY if provided

Document results → TTP_SEARCH_FINDINGS.

Step 5: Enrich Findings

If hits found (IOC_SEARCH_FINDINGS or TTP_SEARCH_FINDINGS):

Read the full file on GitHub · 146 lines

Changes

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 · 146 lines · 67 tokens per session scan A 3c0ff8050c24

Subscribe to this mod's changes

hunt-apt is a skill published in the GitHub repository dandye/ai-runbooks (124 stars, last pushed 27d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,104 once invoked, about $0.0003 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.

Research Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens