claude

spotlight

OSINT investigation orchestration for journalists: structured briefs, methodology approval, sourced findings, independent fact-checking, review artifacts, and knowledge ingestion.

60 on GitHubby Buried Signalsv1.0.0MITupdated 2 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin spotlight in buriedsignals/spotlight. Commands read from the repo's manifest — yesterday.

What it installs

Skills (26)

  • acquisition-graduation

    Convert 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.

  • arbiter

    Use the native Arbiter HTTPS API to browse or create bounded social-media case studies and attach its analytics to a Spotlight report.

  • content-access

    Work through the legal access hierarchy for paywalled or restricted sources before marking them inaccessible and downgrading confidence

  • editorial-review

    Generate a self-contained HTML review artifact after the Investigation gate and export structured feedback to the Investigation gate owner. No server required.

  • epistemic-grounding

    Portable claim-to-evidence grounding for knowledge work, fact-checking, and Spotlight investigations. Use when extracting claims or findings, assigning confidence, diagnosing weak support, or deciding whether material is a lead, partially grounded claim, verified finding, disputed claim, or false cl

  • follow-the-money

    Financial investigation methodology for journalists — corporate ownership, offshore structures, budgets, assets, and public blockchain tracing.

  • ingest

    Retired 1.0 ingest. A findings contract 1.0 case is no longer ingested; it is activated or continued as a follow-up 1.1 case.

  • integrations

    Use when an investigation step may need an external integration such as browser acquisition, Maigret account discovery, Junkipedia narrative tracking, Apify social-media collection, Arbiter social-media case studies, OSINT Navigator tool discovery, Noosphere C2PA signing, or Unpaywall access lookup.

  • investigation-methodology

    Investigation methodology for journalists — step-by-step techniques, platform OPSEC, and case studies from Bellingcat training materials.

  • monitoring

    Turn investigation findings into explicit, user-approved monitoring recommendations. Spotlight recommends; Mycroft owns any Scoutpost action.

  • navigator

    Route investigative research to Navigator when it needs OSINT tool discovery. Use for finding investigative tools and techniques for domains, usernames, images, maps, archives, networks, verification, geolocation, company intelligence, and country-specific research.

  • osint

    OSINT investigation toolkit — local SQL index of 12,500 tools (`osint-tools find`, offline), methodology guides, and optional OSINT Navigator (subscription tier). Works offline with any LLM.

  • phase-ingest

    Spotlight Ingest: resolver-owned transition, ingestion.json status lifecycle, user confirmation, wiki write or decline

  • phase-investigation-gate

    Spotlight Investigation gate (end of Investigation): generate summary.md + data/summary.json, present findings to the user, iterate on request, user approval gate (ends the turn), provenance packaging, review artifact, feedback processing on resume

  • phase-investigation

    Spotlight Investigation — autonomous investigation cycles (max 3, then one targeted research round for a researched case): source-expression release mode resolution, investigator EXECUTION + fact-checker spawns, validators, editorial checks, monitoring recommendations, readiness criteria; includes t

  • phase-methodology

    Spotlight Brief and Methodology: user brief conversation with approval gate, then investigator PLANNING spawn, methodology validation, RLM proposal (frontier opt-in), methodology approval gate

  • phase-preflight

    Spotlight Preflight: config detection, sovereign search/fetch backing checks, OSINT skill inventory, OpenKnowledge workspace validation, project setup, integration tiering, resume feedback check

  • phase-report

    Spotlight Report — public-facing report drafting via report-drafting + finalize-report.py deterministic rendering; hybrid data-detective handover mode

  • phase-research

    Spotlight Research (between Methodology and Investigation): code runs the approved topic briefs as research lanes, merges and triages their leads, the investigator suggests marks, the member marks clues and directions at the Research gate, and AMENDMENT mode turns the marks into the methodology chan

  • provenance-signing

    Build a Spotlight provenance manifest and optionally hand it to Noosphere C2PA signing before the final review/report artifact is delivered.

  • report-drafting

    Report-phase hybrid synthesis — the model authors localized report framing and priority in report-draft.json; deterministic code validates finding references and renders the final Markdown, HTML, and evidence ledger.

  • shell-safety

    Portable safe command construction for any agent skill or recipe. Use before a shell call containing user, model, scraped, configuration, filesystem, or generated values.

  • social-media-intelligence

    Account authenticity assessment, coordination detection, and narrative tracking for social media investigations. Use when analyzing account networks, detecting bot activity or coordinated campaigns, tracking how claims spread across platforms, or building evidence trails from social content.

  • spotlight

    OSINT investigation orchestrator — guides verified investigations from lead to findings to knowledge ingestion. Triggers on "investigate", "investigation", "OSINT", "look into", "dig into".

  • technical-investigation

    Passive technical methods for indicators, infrastructure history, local files, email headers, public GitHub, and verified export.

  • web-archiving

    Archive evidence before it disappears — first-party snapshot (MHTML + screenshot, content-addressed) by default, plus third-party archives, with chain of custody for editorial accountability and legal defensibility

Subagents (4)

  • analyst

    Spotlight's contract for the analyst: from the approved case, writes the Investigation gate summary and the report draft (Pi harness) and proposes the parts of the knowledge batch that need judgment at Ingest

  • fact-checker

    Independent verification of investigation findings using SIFT methodology

  • investigator

    Plans and executes OSINT investigations using open-source intelligence methods

  • researcher

    Works one approved research topic brief: searches and reads public sources (or the local corpus) and returns leads with captured sources

View source on GitHub spotlight.buriedsignals.com

Similar plugins

Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP

5 skills · 1 command · 4 agents

ruvnet/ruflo 81,589

Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain

12 skills · 11 agents · hooks

anthropics/claude-plugins-official 47,076

Honeycomb

claudecodex

Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to complement the Honeycomb MCP server.

11 skills · 1 command · 2 agents · 1 MCP server · hooks

anthropics/knowledge-work-plugins 35,601

Light-prompt reflection skill. Single forcing question + structured journal capture. Path-B sibling of capture from megaprompt 08.

1 skill · 1 command · 1 agent

alirezarezvani/claude-skills 29,725

Reviews hires and terminations for jurisdiction-specific risk flags, classifies workers against the controlling state test, tracks leave deadlines before they're missed, runs internal investigations, and drafts policies with state supplements where the law differs.

20 skills · 1 agent · 2 MCP servers

anthropics/claude-for-legal 9,991

Configures mewt or muton campaigns, analyzes surviving mutants, and investigates bugs exposed by testing gaps. Use when setting up mutation testing, reviewing campaign results, identifying equivalent mutants, or finding bugs from surviving mutations.

1 skill

trailofbits/skills 8,166

Maintain spotlight?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted