dossier-collect
Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel
Best for Open-ended investigationWorks with GitHub
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Graph-structured dossier building
- ·Recursive parallel expansion
- ·Multiple source types: web, memory, codebase, ADR, git
- ·Provenance tracking per claim
- ·Configurable depth, breadth, and budget
Use Cases
- →Investigate a username to find all related accounts, commits, and documents
- →Trace a symbol across the codebase and linked ADRs
- →Explore connections around a concept using multiple sources
Best for
- ✓Open-ended investigation
- ✓Entity relationship discovery
- ✓Cross-source analysis
Not ideal for
- !Specific question answering
- !Single-step tasks
- !Simple lookups
FAQs
name
dossier-collect
description
Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel
argument-hint:<seed> [--max-depth N] [--max-breadth N] [--sources s1,s2] [--budget-usd N] [--exact]
allowed-tools:mcp__claude-flow__memory_store mcp__claude-flow__memory_search mcp__claude-flow__memory_search_unified mcp__claude-flow__agentdb_pattern-search mcp__claude-flow__agentdb_pattern-store mcp__claude-flow__agentdb_hierarchical-recall mcp__claude-flow__embeddings_search mcp__claude-flow__hooks_intelligence_pattern-search mcp__claude-flow__hooks_intelligence_pattern-store mcp__claude-flow__hooks_intelligence_trajectory-start mcp__claude-flow__hooks_intelligence_trajectory-step mcp__claude-flow__hooks_intelligence_trajectory-end mcp__claude-flow__task_create Bash WebSearch WebFetch Read Write Grep Glob
Dossier Collect
Recursive parallel investigation that builds a graph-structured dossier on a seed entity.
When to use
You have a seed (a username, file, symbol, ADR-id, URL, or concept) and want to expand outward discovering every connected entity, with provenance per claim — rather than answering a specific question.
For specific questions use deep-research. For multi-step plans use goal-plan.
Steps
- Detect seed type — classify as one of:
username(handle),file(path),symbol(code identifier),adr(ADR-NNN),url, orconcept(free text). - Pick sources — match the source matrix to the seed type. Default: all applicable.
- Start trajectory — call
mcp__claude-flow__hooks_intelligence_trajectory-startwith taskdossier:<slug>. - Round 0 fan-out — issue ALL source queries in ONE message. Examples:
- For
username:WebSearch,WebFetchon github.com/<user>,mcp__claude-flow__memory_search_unified - For
adr:ReadADR file,Grepreferences,mcp__claude-flow__memory_searchnamespaceadr - For
symbol:Grep,Glob,mcp__claude-flow__embeddings_search
- For
$install
1-click copynpx skills add ruvnet/ruflo --skill dossier-collectSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.