Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Orchestrate OSINT investigations for journalism: automate structured briefs, sourced findings, methodology approval, independent fact-checking, evidence archiving, and tamper-evident review artifacts from a single pipeline.
npx claudepluginhub buriedsignals/spotlight --plugin spotlightConvert repeated dev-browser acquisition successes into durable Spotlight acquisition guidance. Use after a non-trivial browser acquisition works repeatedly and should become a reusable source/domain path without storing secrets, cookies, or fragile session details.
Work through the legal access hierarchy for paywalled or restricted sources before marking them inaccessible and downgrading confidence
Claim-to-evidence grounding for Spotlight investigations. Use when extracting findings, assigning confidence, fact-checking claims, diagnosing weak support, or deciding whether a signal is a lead, partially grounded claim, verified finding, disputed claim, or false claim.
Financial investigation methodology for journalists — corporate ownership tracing, offshore structures, budget monitoring, and asset tracing.
Archive investigation findings into a Markdown vault (Obsidian, Tolaria, or directory) as structured knowledge — entity notes, methodology notes, tool notes, with registries and wikilinks. Works standalone or as part of the Spotlight pipeline.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
OSINT investigation orchestrator with verified findings pipeline and Obsidian knowledge ingestion
30 specialized journalism agents for investigative reporting, fact-checking, disinformation analysis, AI content detection, foreign news de-biasing, bot & troll detection, multimedia production, and content distribution
Tools for investigative journalism: Python script execution, data preprocessing with provenance tracking, and transparent data analysis
Accumulates project knowledge across sessions and developers through structured lessons and hooks
AI-powered deep research with multi-agent source verification and structured outputs
Research sprint orchestrator for Claude Code. Structured research with claims, evidence tiers, and compiled output.
OSINT investigation orchestrator with verified findings pipeline and Obsidian knowledge ingestion
OSINT investigation toolkit for journalists — 150 curated tools with methodology guides and OSINT Navigator integration
Scroll-driven narrative tools for journalists
Spotlight turns an investigation lead into a structured case file: scoped brief, approved methodology, sourced findings, independent fact-checking, review artifacts, provenance records, and handoff-ready knowledge.
It is built for active OSINT casework. Give it a lead, URL, document, entity, or question; it creates a working case directory, gathers source material, tests claims against evidence, and stops at editorial gates instead of quietly treating unfinished leads as publishable facts. The active case workspace is separate from the knowledge vault: Spotlight queries the vault for prior context when a case starts, and ingests verified material into the vault only after an explicit end-of-case decision.
Preflight
-> Brief
-> Methodology
-> Research and fact-check cycles
-> Gate 1 review
-> Ingest, monitor, export, or continue
Every gate is explicit. Spotlight does not auto-advance through brief approval, methodology approval, Gate 1 review, or vault ingestion.
The research loop runs up to five cycles by default:
See docs/investigating.md for the full phase and gate contract.
Spotlight only opens Gate 1 when the case has passed six editorial checks:
These checks are not a truth guarantee. They are a forcing function that keeps the case file honest about what is known, what is unsupported, and what still needs reporting.
Each investigation gets an isolated working directory under the configured
SPOTLIGHT_CASES_ROOT active case workspace:
{CASE_DIR}/
├── brief-directions.txt
├── summary.md
├── review.html
├── data/
│ ├── methodology.json
│ ├── findings.json
│ ├── fact-check.json
│ ├── evidence-bundle.json
│ ├── investigation-log.json
│ ├── summary.json
│ ├── provenance-manifest.json
│ └── monitoring.json
├── research/
│ ├── *.md
│ ├── *.json
│ └── archived/
└── evidence/
├── *.png
└── *.pdf
The JSON files validate against schemas in schemas/. The markdown and HTML files are for human review. The evidence and research folders preserve the local trail behind the claims.
Spotlight's default source path is simple:
Use dev-browser only for specific investigative tasks that require browser
automation: dynamic pages, search forms, authenticated portals, rendered tables,
downloads, visual evidence, or multi-step UI navigation. Firecrawl remains the
first acquisition path for ordinary search and scrape work.
Spotlight is runtime-agnostic, but investigations need specialized tools. The important integrations are: