agentleFS
Liberty91LTDLiberty91LTD/cti-skills/skills/cti-hyperloop/SKILL.md

cti-hyperloop

Skill35 starsChanged 44 days agoMITView on GitHub

Use when the user asks about the CTI Hyperloop framework, the intelligence lifecycle as a high-tempo loop, or how to map intelligence work across strategic / operational / tactical levels with bidirectional feedback. Liberty91's operational doctrine.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the orchestrator receives a task, it maps it to the Hyperloop:

    line 117

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CTI Hyperloop Framework

The CTI Hyperloop (based on Google/Mandiant's practical implementation framework) extends the traditional intelligence cycle by running it at three levels simultaneously with continuous bidirectional feedback.

Core Concept

Traditional intelligence cycle: linear, single-track, often stuck at the tactical level. Hyperloop: three parallel tracks (strategic, operational, tactical) feeding each other continuously.

STRATEGIC  ←→  OPERATIONAL  ←→  TACTICAL
    ↓              ↓               ↓
Direction → Collection → Processing → Analysis → Dissemination → Feedback
    ↑                                                              |
    └──────────────────────────────────────────────────────────────┘

Intelligence Levels

Strategic Intelligence

  • Time horizon: 6-24 months
  • Consumers: CISO, Board, Risk Management, Security Architecture
  • Focus: Threat landscape trends, emerging threats, geopolitical developments, sector risk posture
  • Products: Threat landscape reports, strategic assessments, horizon scanning reports, maturity assessments
  • Example PIR: "How will the ransomware threat landscape evolve over the next 12 months and what are the implications for our risk posture?"

Operational Intelligence

  • Time horizon: Weeks to months
  • Consumers: SOC Manager, IR Lead, Security Operations
  • Focus: Active campaigns, threat actor profiling, TTP analysis, vulnerability exploitation trends
  • Products: Campaign reports, threat actor profiles, operational assessments, hunt packages
  • Example PIR: "What TTPs are currently being used by groups targeting our sector?"

Tactical Intelligence

  • Time horizon: Hours to days
  • Consumers: SOC Analysts, Detection Engineers, IR Analysts
  • Focus: IOCs, detection rules, immediate response support, indicator enrichment
  • Products: IOC packages, SIGMA/YARA/KQL rules, flash reports, enrichment reports
  • Example PIR: "What IOCs are associated with the current wave of attacks targeting our VPN appliances?"

Phase Mapping to Platform

Phase 1: Planning & Direction

What: Define what intelligence is needed and set priorities.

LevelActivityAgentSkills
StrategicSet/review PIRs, horizon scanning briefsorchestratorpir-management, stakeholder-management
OperationalDefine collection priorities for active investigationsorchestratorpir-management, sops
TacticalIdentify IOC collection gaps, detection coverage gapsorchestratorsops

Phase 2: Collection

What: Gather raw data from relevant sources.

LevelActivityAgentSkills
StrategicTrend monitoring, landscape researchosint-researcherosint-methodology
OperationalThreat actor tracking, campaign research, dark web monitoringosint-researcher, tool agentsosint-methodology, darkweb-collection
TacticalIOC lookups, bulk enrichmenttool agents, ioc-processortool-api skills, ioc-enrichment-workflow

Phase 3: Processing

What: Normalise, deduplicate, and structure collected data.

LevelActivityAgentSkills
AllIOC deduplication, format normalisation, source assessment taggingioc-processorioc-enrichment-workflow, source-assessment

Phase 4: Analysis

What: Apply human judgment to produce assessed intelligence.

LevelActivityAgentSkills
StrategicHorizon scanning, maturity assessment, trend analysisanalysthorizon-scanning, threat-assessment, maturity-assessment
OperationalACH, threat actor profiling, campaign trackinganalystach, threat-actor-profiling, campaign-tracking, key-assumptions-check
TacticalIOC correlation, detection gap analysis, indicator pivotinganalystindicator-pivoting, vulnerability-intelligence

Phase 5: Dissemination

What: Deliver finished intelligence to stakeholders.

LevelActivityAgentSkills
StrategicLandscape reports, annual assessments, board briefingsreport-writerintelligence-writing, writing-assessments, stakeholder-management
OperationalActor profiles, campaign reports, operational assessmentsreport-writerintelligence-writing, writing-assessments
TacticalIOC packages, detection rules, flash reportsdetection-engineer, ioc-processor, report-writersigma/yara/kql-writing, ioc-export, stix-bundle

Phase 6: Feedback

What: Assess effectiveness and refine direction.

LevelActivityAgentSkills
AllConsumer feedback, source quality tracking, PIR refinementorchestratorfeedback-loops, pir-management

Bidirectional Flow Examples

Tactical → Operational: IOC enrichment reveals infrastructure pattern shared across multiple incidents → triggers campaign tracking investigation.

Operational → Strategic: Campaign analysis identifies new nation-state actor shifting targeting to a new sector → feeds into strategic landscape assessment and PIR update.

Strategic → Operational: Horizon scanning identifies AI-augmented social engineering as emerging threat → creates operational collection tasking for specific TTP monitoring.

Operational → Tactical: Threat actor profiling reveals preferred exploitation technique → drives creation of specific SIGMA detection rules.

Strategic → Tactical: Risk assessment identifies unpatched VPN as critical exposure → prioritises vulnerability intelligence and IOC monitoring for VPN exploits.

Tactical → Strategic: Spike in credential-stuffing alerts → informs strategic assessment of the underground economy and infostealer trend.

Orchestrator Workflow Mapping

When the orchestrator receives a task, it maps it to the Hyperloop:

User RequestPrimary LevelHyperloop PhasesKey Agents
"Investigate this IP"Tactical2→3→4→5Tool agents → IOC processor → Analyst → Detection engineer
"Profile this threat actor"Operational2→3→4→5→6OSINT researcher → IOC processor → Analyst → Report writer → Update knowledge cell
"Write a threat assessment on X"Strategic/Operational1→2→3→4→5→6Orchestrator (PIRs) → OSINT researcher → Analyst (SATs) → Report writer → Quality reviewer
"Enrich this IOC list"Tactical2→3→5Tool agents → IOC processor → Export
"What's the current ransomware landscape?"Strategic2→4→5OSINT researcher → Analyst (knowledge cell) → Report writer
"Create detection rules for APT28 TTPs"Tactical4→5Analyst (knowledge cell) → Detection engineer
"Review our PIRs"Management1→6Orchestrator (PIR management, feedback loops)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.