By assafkip
Run structured digital investigations and OSINT research within Claude Code — manage cases, collect evidence from platforms like LinkedIn and Telegram, apply CIA tradecraft analytic techniques, map relationships, and export findings as markdown, JSON, or interactive timelines.
Review all collected data and surface patterns, connections, and gaps.
Start a new investigation session. Read all state files to load context before doing anything.
Generate a structured investigation brief summarizing current state.
Force a structured challenge of all investigation assumptions and hypotheses.
Save current investigation state. Run at the end of every session.
Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external. Use when: "osint", "research person", "find everything about", "due diligence", "background check", "digital footprint", "dossier", "profile someone". NOT for: company/product research without a named person, competitive analysis, market research, content generation, or general web scraping tasks.
Conduct structured analysis on any problem using CIA/IC analytic techniques — assess competing hypotheses, challenge assumptions, stress-test judgments, and produce defensible evidence-based assessments with full citations. Supports 18 techniques including ACH, Key Assumptions Check, What-If, Premortem, Cross-Impact Matrix, Contrasting Narratives, Devil's Advocacy, Red Hat Analysis, Alternative Futures, and Deception Detection.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Investigation toolkit for Claude Code. Case management, OSINT, structured analytic techniques, chain-of-custody evidence capture, and bundled MCP servers for infrastructure recon and threat intel.
Not just a scraper wrapper. A full investigation workflow — from case intake to evidence-grade dossier.
Use it for: OSINT, due diligence, threat intelligence, incident response, digital forensics, journalistic research, competitive intel, security research, CTF challenges.
flowchart LR
Start([New case]) --> NewCase[/q-new-case/]
NewCase --> Scope[/q-scope/]
Scope --> Begin[/q-begin/]
Begin --> Collect{Collection}
Collect --> Intake[/q-intake<br/>client docs/]
Collect --> OSINT[/q-osint<br/>platform-targeted/]
Collect --> Sweep[/q-collect<br/>broad sweep/]
Collect --> Target[/q-target<br/>profile/]
Intake --> Evidence[(EV-NNNN<br/>evidence items<br/>Wayback + archive.today<br/>+ Chrome PDF + SHA-256)]
OSINT --> Evidence
Sweep --> Evidence
Target --> Evidence
Evidence --> Analyze{Analysis}
Analyze --> Timeline[/q-timeline/]
Analyze --> Link[/q-link<br/>graph edges/]
Analyze --> ACH[/q-analyze<br/>Heuer's ACH/]
Analyze --> Challenge[/q-challenge<br/>red team/]
Analyze --> Reality[/q-reality-check/]
Timeline --> Report{Report}
Link --> Report
ACH --> Report
Challenge --> Report
Reality --> Report
Report --> Brief[/q-brief<br/>evidence-cited/]
Report --> Debrief[/q-debrief<br/>internal/]
Brief --> Export[/q-export/]
Debrief --> Export
Export --> End([Dossier delivered])
style Evidence fill:#fef3c7,stroke:#d97706,stroke-width:2px
style Start fill:#dbeafe,stroke:#2563eb
style End fill:#dcfce7,stroke:#16a34a
Every URL routes through capture-evidence.sh. Every finding cites [EV-NNNN]. Every claim has an A-F reliability grade.
graph TB
subgraph Claude[Claude Code]
CC[/Claude Code session/]
end
subgraph huntkit[huntkit plugin]
direction TB
subgraph Skills
OSINT_S[osint<br/>6-phase workflow]
SA_S[structured-analysis<br/>Heuer's ACH + tradecraft primer]
end
subgraph Commands[22 commands]
CM[case mgmt]
CL[collection]
AN[analysis]
RP[reporting]
end
subgraph Rules[Enforced rules]
EC[evidence-capture-protocol]
QI[q-investigation]
TD[token-discipline]
SY[sycophancy]
end
subgraph Templates
NI[new-investigation]
SS[sec-stack-case]
end
end
subgraph MCP[Bundled MCP servers]
OI[osint-infra<br/>whois, dns, wayback]
TI[threat-intel<br/>VT, URLhaus, ThreatFox, crt.sh]
end
subgraph External[Optional external APIs]
PPL[Perplexity]
EXA[Exa]
TAV[Tavily]
APF[Apify<br/>55+ scrapers]
JIN[Jina]
BD[Bright Data]
end
subgraph Case[Case workspace]
EVD[(investigations/case/<br/>evidence/ findings/<br/>targets/ timelines/)]
end
CC --> huntkit
huntkit --> MCP
huntkit --> External
huntkit --> Case
Rules -.enforces.-> Commands
Commands -.uses.-> Skills
style Case fill:#fef3c7,stroke:#d97706
style MCP fill:#e0e7ff,stroke:#6366f1
style Rules fill:#fee2e2,stroke:#dc2626
osint — 6-phase investigation: tooling check → seed collection → optional internal intel → platform extraction → cross-reference → psychoprofile → completeness scoring → dossier.structured-analysis — CIA tradecraft primer library (Heuer's ACH, key assumptions check, quality of information check, red team, premortem, 66-technique taxonomy). Apache 2.0, upstream Blevene/structured-analysis-skill.Case management: /q-new-case, /q-scope, /q-begin, /q-status, /q-checkpoint, /q-handoff, /q-end
Collection: /q-intake, /q-collect, /q-osint, /q-target, /q-screenshots
Analysis: /q-analyze, /q-challenge, /q-reality-check, /q-client-questions, /q-timeline, /q-link
Reporting: /q-brief, /q-debrief, /q-export
Specialized: /q-sec-stack (SaaS security stack intel)
npx claudepluginhub assafkip/huntkitAnti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements, source grounding, and 'I don't know' behavior.
Design skills: UI/UX, brand identity, visual assets
Entrepreneur OS core: AUDHD executive function, voice enforcement, and research mode
Entrepreneur OS operations: council debates, customer fit reviews
PRD operating system with DSSE execution: capture rough ideas, draft reviewable PRDs, run Codex review + adversarial review, triage findings, decompose into atomic issue specs, and execute those issues with scope enforcement, receipts, and Codex review. Ships /prd-start, /prd-review, /prd-approve, /prd-triage, /prd-split, /issue-start, /issue-approve, /issue-verify, /issue-review, /issue-amend, /issue-closeout.
OSINT investigation orchestrator with verified findings pipeline and Obsidian knowledge ingestion
AI-augmented Structured Analytic Techniques from US Intelligence Community doctrine — 18 techniques across 6 phases with automated evidence gathering, self-correction, and citation enforcement
Interprets Culture Index survey results for individuals and teams
Offensive security toolkit for Claude Code — Neo4j intel graph, strategic compaction, multi-agent orchestration, and post-engagement debriefs
Cyberbro IOC analysis toolkit. Extract, enrich, and analyze observables with 5 MCP tools.
Research sprint orchestrator for Claude Code. Structured research with claims, evidence tiers, and compiled output.