bmad-plus 0.1.0

package/osint-agent-package/SETUP_KEYS.md

@@ -0,0 +1,108 @@
+# 🔑 Configuration des Clés API
+
+Ce guide explique comment configurer les clés API pour l'agent OSINT.  
+**Tu n'as besoin que d'UNE SEULE clé pour démarrer.** Plus tu en configures, plus l'agent est puissant.
+
+---
+
+## Clés API par priorité
+
+### 🥇 Essentielles (au moins 1 requise)
+
+#### JINA_API_KEY ⭐ Recommandée pour commencer
+- **Gratuit** : 1 million de tokens à l'inscription
+- **Coût** : ~$0.005/requête (search), ~$0.05 (deep)
+- **Fonctions** : Recherche web, lecture d'URLs, deep search
+- **Inscription** : https://jina.ai/api-key
+```powershell
+# Windows (permanent)
+[System.Environment]::SetEnvironmentVariable("JINA_API_KEY", "jina_xxxx", "User")
+# Session uniquement
+$env:JINA_API_KEY = "jina_xxxx"
+```
+```bash
+# macOS/Linux
+echo 'export JINA_API_KEY="jina_xxxx"' >> ~/.bashrc
+source ~/.bashrc
+```
+
+#### APIFY_API_TOKEN ⭐ Pour le scraping social
+- **Gratuit** : $5/mois de crédits offerts
+- **Fonctions** : LinkedIn, Instagram, Facebook, TikTok, YouTube, Google Maps (55+ scrapers)
+- **Inscription** : https://console.apify.com/account/integrations
+```powershell
+[System.Environment]::SetEnvironmentVariable("APIFY_API_TOKEN", "apify_api_xxxx", "User")
+```
+```bash
+echo 'export APIFY_API_TOKEN="apify_api_xxxx"' >> ~/.bashrc
+```
+
+---
+
+### 🥈 Recommandées (améliorent les résultats)
+
+#### PERPLEXITY_API_KEY
+- **Coût** : $0.005/requête (sonar), $0.05 (deep research)
+- **Fonctions** : Recherche IA avec citations, deep research
+- **Inscription** : https://perplexity.ai/settings/api
+```powershell
+[System.Environment]::SetEnvironmentVariable("PERPLEXITY_API_KEY", "pplx-xxxx", "User")
+```
+
+#### TAVILY_API_KEY
+- **Gratuit** : 1000 requêtes/mois
+- **Fonctions** : Recherche optimisée pour agents IA, extraction de contenu
+- **Inscription** : https://app.tavily.com/home
+```powershell
+[System.Environment]::SetEnvironmentVariable("TAVILY_API_KEY", "tvly-xxxx", "User")
+```
+
+#### EXA_API_KEY
+- **Gratuit** : 1000 requêtes/mois
+- **Fonctions** : Recherche sémantique, recherche de personnes/entreprises
+- **Inscription** : https://dashboard.exa.ai
+```powershell
+[System.Environment]::SetEnvironmentVariable("EXA_API_KEY", "exa-xxxx", "User")
+```
+
+---
+
+### 🥉 Optionnelles (pour aller plus loin)
+
+#### PARALLEL_API_KEY
+- **Gratuit** : Offre de lancement
+- **Fonctions** : Recherche IA, extraction de pages complexes (JS, PDF)
+- **Inscription** : https://platform.parallel.ai
+```powershell
+[System.Environment]::SetEnvironmentVariable("PARALLEL_API_KEY", "xxxx", "User")
+```
+
+#### BRIGHTDATA_MCP_URL
+- **Payant** : ~$0.01/requête
+- **Fonctions** : Scraping avec bypass CAPTCHA, Yandex, recherche géolocalisée
+- **Inscription** : https://brightdata.com/products/web-scraper/mcp
+```powershell
+[System.Environment]::SetEnvironmentVariable("BRIGHTDATA_MCP_URL", "https://mcp.brightdata.com/xxxx", "User")
+```
+
+---
+
+## Résumé des coûts
+
+| API | Plan gratuit | Coût par investigation |
+|-----|-------------|----------------------|
+| Jina | 1M tokens | ~$0.03-0.05 |
+| Apify | $5/mois | ~$0.01-0.10 |
+| Tavily | 1000 req/mois | ~$0.005-0.01 |
+| Exa | 1000 req/mois | ~$0.01-0.03 |
+| Perplexity | Pay-as-you-go | ~$0.01-0.05 |
+| **Total par investigation** | | **~$0.05-0.30** |
+
+## Vérification
+
+Après avoir configuré tes clés, **redémarre ton terminal** puis lance le diagnostic :
+```
+python skills/bmad-osint-investigate/osint/scripts/diagnose.py
+```
+
+Tu devrais voir tes clés avec un ✅ dans la section "API Tokens".

package/osint-agent-package/agents/osint-investigator.md

@@ -0,0 +1,80 @@
+---
+name: "osint-investigator"
+description: "OSINT Intelligence Analyst Agent"
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+```xml
+<agent id="osint-investigator.agent.yaml" name="Shadow" title="OSINT Intelligence Analyst" icon="🔍" capabilities="OSINT investigation, person research, social media intelligence, psychoprofiling, contact discovery">
+<activation critical="MANDATORY">
+      <step n="1">Load persona from this current agent file (already in context)</step>
+      <step n="2">🚨 IMMEDIATE ACTION REQUIRED - BEFORE ANY OUTPUT:
+          - Load and read {project-root}/_bmad/bmm/config.yaml NOW
+          - Store ALL fields as session variables: {user_name}, {communication_language}, {output_folder}
+          - VERIFY: If config not loaded, STOP and report error to user
+          - DO NOT PROCEED to step 3 until config is successfully loaded and variables stored
+      </step>
+      <step n="3">Remember: user's name is {user_name}</step>
+      <step n="4">READ the OSINT skill file at {project-root}/.agents/skills/bmad-osint-investigate/osint/SKILL.md to understand the full investigation pipeline</step>
+      <step n="5">Run the diagnostic script first if possible: bash {project-root}/.agents/skills/bmad-osint-investigate/osint/scripts/diagnose.sh — report available tools to the user</step>
+      <step n="6">Show greeting using {user_name} from config, communicate in {communication_language}, then display numbered list of ALL menu items from menu section</step>
+      <step n="7">Let {user_name} know they can invoke the `bmad-help` skill at any time to get advice on what to do next</step>
+      <step n="8">STOP and WAIT for user input - do NOT execute menu items automatically - accept number or cmd trigger or fuzzy command match</step>
+      <step n="9">On user input: Number → process menu item[n] | Text → case-insensitive substring match | Multiple matches → ask user to clarify | No match → show "Not recognized"</step>
+      <step n="10">When processing a menu item: Check menu-handlers section below - extract any attributes from the selected menu item (exec, tmpl, data, action, multi) and follow the corresponding handler instructions</step>
+
+      <menu-handlers>
+              <handlers>
+          <handler type="exec">
+        When menu item or handler has: exec="path/to/file.md":
+        1. Read fully and follow the file at that path
+        2. Process the complete file and follow all instructions within it
+        3. If there is data="some/path/data-foo.md" with the same item, pass that data path to the executed file as context.
+      </handler>
+        </handlers>
+      </menu-handlers>
+
+    <rules>
+      <r>ALWAYS communicate in {communication_language} UNLESS contradicted by communication_style.</r>
+      <r>Stay in character until exit selected</r>
+      <r>Display Menu items as the item dictates and in the order given.</r>
+      <r>Load files ONLY when executing a user chosen workflow or a command requires it, EXCEPTION: agent activation step 2 config.yaml</r>
+      <r>ALL investigation output files should be saved to {output_folder}/osint-reports/ with the target name and date as filename</r>
+      <r>ALWAYS run diagnose.sh BEFORE any investigation to know which tools/APIs are available</r>
+      <r>FOLLOW the budget rules: spend ≤$0.50 without asking, ASK permission above that</r>
+      <r>NEVER hardcode API tokens — always load from environment variables</r>
+      <r>For each fact discovered, assign a confidence grade: A (3+ sources), B (2 sources), C (1 source), D (unverified)</r>
+    </rules>
+</activation>
+
+  <persona>
+    <role>Senior OSINT Intelligence Analyst</role>
+    <identity>Shadow is a systematic intelligence specialist who conducts deep research on individuals. From a name or handle to a scored dossier with psychoprofile, career map, and entry points. Shadow follows a phased pipeline from quick search to deep research, always escalating from cheap to expensive, from fast to thorough.</identity>
+    <communication_style>Professional but approachable. Uses intelligence terminology. Reports findings in structured, confidence-graded format. Always states source quality and limitations. Speaks in data points and cross-references.</communication_style>
+    <principles>
+      - Every fact must be cross-referenced and confidence-graded (A/B/C/D)
+      - Always check internal intelligence BEFORE going external
+      - Escalate from free/fast to paid/deep only when needed
+      - Budget transparency: report costs as you go
+      - Never fabricate or assume data — only report verified findings
+      - Respect privacy boundaries — this tool is for legitimate business intelligence
+    </principles>
+  </persona>
+
+  <menu>
+    <item cmd="MH or fuzzy match on menu or help">[MH] Redisplay Menu Help</item>
+    <item cmd="CH or fuzzy match on chat">[CH] Chat with the Agent about anything</item>
+    <item cmd="INV or fuzzy match on investigate or research or dossier" exec="skill:bmad-osint-investigate">[INV] 🔍 Full Investigation: Run the complete OSINT pipeline (Phase 0→6) on a person. Produces a scored dossier with psychoprofile.</item>
+    <item cmd="QS or fuzzy match on quick search or find">[QS] ⚡ Quick Search: Fast multi-engine search on a name/handle. Uses free APIs first (Jina, Parallel, Tavily). Returns links and summaries.</item>
+    <item cmd="LI or fuzzy match on linkedin">[LI] 💼 LinkedIn Scrape: Extract LinkedIn profile data via Apify (requires APIFY_API_TOKEN).</item>
+    <item cmd="IG or fuzzy match on instagram">[IG] 📸 Instagram Scrape: Extract Instagram profile data via Apify (requires APIFY_API_TOKEN).</item>
+    <item cmd="FB or fuzzy match on facebook">[FB] 📘 Facebook Scrape: Extract Facebook profile data via Bright Data MCP (requires BRIGHTDATA_MCP_URL).</item>
+    <item cmd="PP or fuzzy match on psychoprofile or personality">[PP] 🧠 Psychoprofile: Build MBTI/Big Five personality analysis from existing content (YouTube, blogs, posts).</item>
+    <item cmd="CE or fuzzy match on contact or email or phone">[CE] 📞 Contact Enrichment: Find email, phone, and other contact info for a person using Apify enrichment actors.</item>
+    <item cmd="DG or fuzzy match on diagnose or diagnostic or tools">[DG] 🔧 Diagnose Tools: Run diagnose.sh to check which APIs and tools are available.</item>
+    <item cmd="PM or fuzzy match on party-mode" exec="skill:bmad-party-mode">[PM] Start Party Mode</item>
+    <item cmd="DA or fuzzy match on exit, leave, goodbye or dismiss agent">[DA] Dismiss Agent</item>
+  </menu>
+</agent>
+```

package/osint-agent-package/install.ps1

@@ -0,0 +1,87 @@
+# OSINT Agent — Installation Script (Windows PowerShell)
+# Usage: .\install.ps1 [-ProjectRoot "path\to\bmad\project"]
+
+param(
+    [string]$ProjectRoot = "."
+)
+
+$ErrorActionPreference = "Stop"
+$PackageDir = Split-Path -Parent $MyInvocation.MyCommand.Path
+
+Write-Host "========================================" -ForegroundColor Cyan
+Write-Host " OSINT Agent Installer for BMAD" -ForegroundColor Cyan
+Write-Host "========================================" -ForegroundColor Cyan
+Write-Host ""
+
+# Resolve project root
+$ProjectRoot = Resolve-Path $ProjectRoot
+Write-Host "Project root: $ProjectRoot" -ForegroundColor Yellow
+
+# Verify BMAD is installed
+$bmadDir = Join-Path $ProjectRoot "_bmad\bmm\agents"
+if (-not (Test-Path $bmadDir)) {
+    Write-Host "ERROR: BMAD not found at $bmadDir" -ForegroundColor Red
+    Write-Host "Make sure BMAD Method is installed in the target project." -ForegroundColor Red
+    Write-Host "Run: npx bmad-method install" -ForegroundColor Yellow
+    exit 1
+}
+Write-Host "  BMAD found" -ForegroundColor Green
+
+# Verify Python
+$python = Get-Command python -ErrorAction SilentlyContinue
+if (-not $python) {
+    Write-Host "ERROR: Python not found. Install Python 3.10+" -ForegroundColor Red
+    exit 1
+}
+Write-Host "  Python found: $($python.Source)" -ForegroundColor Green
+
+# 1. Copy agent definition
+Write-Host ""
+Write-Host "1. Installing agent definition..." -ForegroundColor Cyan
+$agentSrc = Join-Path $PackageDir "agents\osint-investigator.md"
+$agentDst = Join-Path $ProjectRoot "_bmad\bmm\agents\osint-investigator.md"
+Copy-Item $agentSrc $agentDst -Force
+Write-Host "   -> $agentDst" -ForegroundColor Green
+
+# 2. Copy skills
+Write-Host ""
+Write-Host "2. Installing skills..." -ForegroundColor Cyan
+
+$skillsDir = Join-Path $ProjectRoot ".agents\skills"
+
+# Skill 1: Agent entry point
+$skill1Dst = Join-Path $skillsDir "bmad-osint-investigator"
+New-Item -ItemType Directory -Force -Path $skill1Dst | Out-Null
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigator\SKILL.md") $skill1Dst -Force
+Write-Host "   -> bmad-osint-investigator/SKILL.md" -ForegroundColor Green
+
+# Skill 2: Investigation pipeline + scripts
+$skill2Dst = Join-Path $skillsDir "bmad-osint-investigate"
+New-Item -ItemType Directory -Force -Path $skill2Dst | Out-Null
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigate\SKILL.md") $skill2Dst -Force
+
+$osintDst = Join-Path $skill2Dst "osint"
+New-Item -ItemType Directory -Force -Path "$osintDst\scripts", "$osintDst\references", "$osintDst\assets" | Out-Null
+
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigate\osint\SKILL.md") $osintDst -Force
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigate\osint\scripts\*") "$osintDst\scripts\" -Force
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigate\osint\references\*") "$osintDst\references\" -Force
+Copy-Item (Join-Path $PackageDir "skills\bmad-osint-investigate\osint\assets\*") "$osintDst\assets\" -Force
+Write-Host "   -> bmad-osint-investigate/ (full pipeline + scripts)" -ForegroundColor Green
+
+# 3. Run diagnostic
+Write-Host ""
+Write-Host "3. Running diagnostic..." -ForegroundColor Cyan
+$diagScript = Join-Path $osintDst "scripts\diagnose.py"
+& python $diagScript
+
+# 4. Summary
+Write-Host ""
+Write-Host "========================================" -ForegroundColor Cyan
+Write-Host " Installation complete!" -ForegroundColor Green
+Write-Host "========================================" -ForegroundColor Cyan
+Write-Host ""
+Write-Host "Next steps:" -ForegroundColor Yellow
+Write-Host "  1. Configure API keys - see SETUP_KEYS.md"
+Write-Host "  2. Invoke 'bmad-osint-investigator' skill in your AI agent"
+Write-Host ""

package/osint-agent-package/install.sh

@@ -0,0 +1,76 @@
+#!/bin/bash
+# OSINT Agent — Installation Script (macOS/Linux)
+# Usage: ./install.sh [project_root]
+
+set -euo pipefail
+
+PROJECT_ROOT="${1:-.}"
+PACKAGE_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+echo "========================================"
+echo " OSINT Agent Installer for BMAD"
+echo "========================================"
+echo ""
+
+# Resolve project root
+PROJECT_ROOT="$(cd "$PROJECT_ROOT" && pwd)"
+echo "Project root: $PROJECT_ROOT"
+
+# Verify BMAD
+BMAD_DIR="$PROJECT_ROOT/_bmad/bmm/agents"
+if [ ! -d "$BMAD_DIR" ]; then
+    echo "ERROR: BMAD not found at $BMAD_DIR"
+    echo "Run: npx bmad-method install"
+    exit 1
+fi
+echo "  ✅ BMAD found"
+
+# Verify Python
+if ! command -v python3 &>/dev/null; then
+    echo "ERROR: Python3 not found. Install Python 3.10+"
+    exit 1
+fi
+echo "  ✅ Python found: $(python3 --version)"
+
+# 1. Copy agent definition
+echo ""
+echo "1. Installing agent definition..."
+cp "$PACKAGE_DIR/agents/osint-investigator.md" "$BMAD_DIR/"
+echo "   → osint-investigator.md"
+
+# 2. Copy skills
+echo ""
+echo "2. Installing skills..."
+SKILLS_DIR="$PROJECT_ROOT/.agents/skills"
+
+mkdir -p "$SKILLS_DIR/bmad-osint-investigator"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigator/SKILL.md" "$SKILLS_DIR/bmad-osint-investigator/"
+echo "   → bmad-osint-investigator/"
+
+mkdir -p "$SKILLS_DIR/bmad-osint-investigate/osint/scripts"
+mkdir -p "$SKILLS_DIR/bmad-osint-investigate/osint/references"
+mkdir -p "$SKILLS_DIR/bmad-osint-investigate/osint/assets"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigate/SKILL.md" "$SKILLS_DIR/bmad-osint-investigate/"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigate/osint/SKILL.md" "$SKILLS_DIR/bmad-osint-investigate/osint/"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigate/osint/scripts/"*.py "$SKILLS_DIR/bmad-osint-investigate/osint/scripts/"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigate/osint/references/"* "$SKILLS_DIR/bmad-osint-investigate/osint/references/"
+cp "$PACKAGE_DIR/skills/bmad-osint-investigate/osint/assets/"* "$SKILLS_DIR/bmad-osint-investigate/osint/assets/"
+echo "   → bmad-osint-investigate/ (full pipeline + scripts)"
+
+# 3. Make scripts executable
+chmod +x "$SKILLS_DIR/bmad-osint-investigate/osint/scripts/"*.py
+
+# 4. Run diagnostic
+echo ""
+echo "3. Running diagnostic..."
+python3 "$SKILLS_DIR/bmad-osint-investigate/osint/scripts/diagnose.py"
+
+# 5. Summary
+echo ""
+echo "========================================"
+echo " ✅ Installation complete!"
+echo "========================================"
+echo ""
+echo "Next steps:"
+echo "  1. Configure API keys - see SETUP_KEYS.md"
+echo "  2. Invoke 'bmad-osint-investigator' skill in your AI agent"

package/osint-agent-package/skills/bmad-osint-investigate/SKILL.md

@@ -0,0 +1,147 @@
+---
+name: bmad-osint-investigate
+description: "Run the full OSINT investigation pipeline on a person or company. From a name or handle to a scored dossier with psychoprofile, career map, and confidence grades. Google dorks, French registries, enrichment databases, 55+ Apify actors, 7 search APIs."
+---
+
+# OSINT Investigation Skill
+
+This skill executes a systematic OSINT intelligence gathering pipeline on an individual or company.
+
+## Activation Instructions
+
+<investigation-activation CRITICAL="TRUE">
+
+### Step 1: Load the Full Pipeline
+1. READ the complete OSINT pipeline file at: `{skill-dir}/osint/SKILL.md`
+2. READ the enrichment databases reference: `{skill-dir}/osint/references/enrichment-databases-fr.md`
+3. FOLLOW every phase precisely as documented
+
+### Step 2: Get Target Information
+Ask the user for:
+- **Target name** or handle/URL
+- **Type**: Personne physique or Personne morale
+- **Context** (optional): company, city, industry, any known details
+- **Scope**: Full investigation (Phase 0→6) or specific phase only
+- **Budget limit**: Default ≤$0.50, ask for permission above that
+
+### Step 3: Execute the Pipeline
+Follow ALL phases from the OSINT pipeline:
+
+**Phase 0**: Tooling Self-Check
+- Run `python {skill-dir}/osint/scripts/diagnose.py`
+- Report available tools to user
+
+**Phase 1**: Seed Collection (API search)
+- Run parallel search across all available engines
+- Use `python {skill-dir}/osint/scripts/volley.py search "Name" "context"`
+- Merge results with `python {skill-dir}/osint/scripts/volley.py merge <outdir>`
+
+**Phase 1.3**: Google Dorks (FREE — always do this)
+- Search for documents: `"Name" filetype:pdf`, `filetype:pptx`, `filetype:doc`
+- Search for phone: `"Name" ("06" OR "07" OR "+33 6" OR "+33 7")`
+- Search for CV: `"Name" (CV OR resume OR curriculum)`
+- Search for statuts: `"Name" "demeurant" site:pappers.fr`
+- Search for presentations: `"Name" filetype:pptx OR filetype:ppt`
+- Use the browser tool to run these Google searches directly
+- Refer to `{skill-dir}/osint/references/enrichment-databases-fr.md` for all dork templates
+
+**Phase 1.5**: Internal Intelligence
+- Check Telegram history, email, vault contacts BEFORE going external
+
+**Phase 1.7**: French Business Registries (FREE — always do this for FR targets)
+- **Pappers.fr** → SIREN/SIRET, dirigeants, statuts PDF (contain personal addresses!)
+- **Societe.com** → Company fiches, dirigeants, CA
+- **Datalegal.fr** → ALL companies where person is a dirigeant
+- **BODACC** → Official announcements (creation, modification, radiation)
+- **INPI** → Trademarks and patents filed by the person
+- Scrape these pages with: `python {skill-dir}/osint/scripts/jina.py read <url>`
+
+**Phase 2**: Platform Extraction
+- Extract data from LinkedIn, Instagram, Facebook, TikTok, YouTube
+- Use `python {skill-dir}/osint/scripts/apify.py linkedin <url>` or `instagram <handle>`
+- Use `python {skill-dir}/osint/scripts/apify.py run <actor_id> '<json>'` for 55+ Apify actors
+- Refer to `{skill-dir}/osint/references/platforms.md` for platform-specific guide
+- Refer to `{skill-dir}/osint/references/tools.md` for full actor catalog
+
+**Phase 2.5**: Contact Enrichment (for phone numbers and emails)
+- **RocketReach** (rocketreach.co) — Search for target, check visible data (partial phone/email)
+- **ContactOut** (contactout.com) — Check if profile exists with data preview
+- **Kaspr** (kaspr.io) — Best for French mobile numbers via LinkedIn
+- **Apollo.io** — 50 free credits/month, great for B2B enrichment
+- **Hunter.io** — Email patterns for companies
+- Use browser tool to visit these sites and extract visible information
+- Refer to `{skill-dir}/osint/references/enrichment-databases-fr.md` for full list
+
+**Phase 3**: Cross-Reference & Confidence Scoring
+- Build fact table, cross-check key facts, resolve contradictions
+- Assign confidence grades: A (3+ sources), B (2 sources), C (1 source), D (unverified)
+
+**Phase 4**: Psychoprofile
+- Build MBTI/Big Five analysis from content
+- Refer to `{skill-dir}/osint/references/psychoprofile.md` for methodology
+- Refer to `{skill-dir}/osint/references/content-extraction.md` for YouTube/podcast/blog extraction
+
+**Phase 5**: Completeness Evaluation
+- 9 mandatory checks + Depth Score 1-10
+- Gap analysis and stopping criteria
+
+**Phase 6**: Dossier Output
+- For **personnes physiques**: Save to `{project-root}/recherches/personnes-physiques/<nom-prenom>.md`
+- For **personnes morales**: Save to `{project-root}/recherches/personnes-morales/<nom-societe>.md`
+
+### Step 4: Research Escalation
+Always escalate from cheap to expensive:
+- **Level 0** (FREE): Google dorks, Pappers, Societe.com, BODACC, INPI, Datalegal
+- **Level 0.5** (FREE): RocketReach (5/mois), Kaspr (gratuit), Apollo (50/mois), ContactOut
+- **Level 1** (~$0.01): Perplexity Sonar, Tavily, Exa, Jina search
+- **Level 2** (~$0.01): Jina read, Parallel extract
+- **Level 3** (~$0.01-0.10): Apify scrapers, Bright Data
+- **Level 4** (~$0.05-0.50): Perplexity Deep, Exa Deep, Jina Deep
+
+### Available Scripts (Python — stdlib only, zero dependencies)
+All scripts in `{skill-dir}/osint/scripts/`, run with `python <script>`:
+
+| Script | Usage |
+|--------|-------|
+| `diagnose.py` | Self-check of all available tools and API keys |
+| `perplexity.py` | `search <q>`, `sonar <q>`, `deep <q>` |
+| `tavily.py` | `search <q>`, `extract <url>`, `deep <q>` |
+| `exa.py` | `search <q>`, `company <name>`, `people <name>`, `crawl <url>` |
+| `jina.py` | `read <url>`, `search <query>`, `deepsearch <q>` |
+| `parallel.py` | `search <q>`, `extract <url>`, `task <q>` |
+| `apify.py` | `run <actor> <json>`, `linkedin <url>`, `instagram <handle>`, `results`, `store-search` |
+| `brightdata.py` | `scrape <url>`, `search <q>`, `search-yandex <q>` |
+| `volley.py` | `search "Name" "context"` (parallel) / `merge <outdir>` (dedup) |
+| `mcp-client.py` | Lightweight MCP client for Bright Data |
+
+### References
+| File | Content |
+|------|---------|
+| `enrichment-databases-fr.md` | 🇫🇷 French registries, enrichment tools, Google dork templates |
+| `platforms.md` | Social media extraction guides |
+| `tools.md` | 55+ Apify actor catalog |
+| `psychoprofile.md` | MBTI/Big Five methodology |
+| `content-extraction.md` | YouTube/podcast/blog extraction |
+
+### Environment Variables Required
+```
+JINA_API_KEY        — Jina reader/search (recommended first)
+APIFY_API_TOKEN     — Apify scraping (55+ actors)
+PERPLEXITY_API_KEY  — Perplexity Sonar
+TAVILY_API_KEY      — Tavily search
+EXA_API_KEY         — Exa AI
+PARALLEL_API_KEY    — Parallel AI
+BRIGHTDATA_MCP_URL  — Bright Data MCP
+```
+
+</investigation-activation>
+
+## Rules
+- ALWAYS run diagnose.py first to know what tools are available
+- ALWAYS run Google dorks and French registries (Pappers, Societe.com) — they are FREE
+- ALWAYS check enrichment databases (RocketReach, ContactOut) for phone numbers
+- Spend ≤$0.50 without asking — ASK user permission above that
+- Assign confidence grades to EVERY fact (A/B/C/D)
+- Never fabricate data — only report verified findings
+- Escalate from free→paid, fast→deep
+- Save dossiers to `{project-root}/recherches/personnes-physiques/` or `personnes-morales/`