Plugin Claude Code
Multi-agent deep research orchestrator with evidence graphs, quality gates, and publication-quality report generation.
2 6mo ago A
tokens not measured
original MIT
dr-analyst
02Agent
Performs deep analysis for deep research runs. Reads sources thoroughly, extracts atomic claims with citations, builds evidence edges for triangulation, and documents conflicts between sources.
2 6mo ago A 37 tokens
original MIT
dr-lead
03Agent
Orchestrates multi-agent Deep Research runs. Decomposes questions, assigns tasks to teammates, enforces evidence quality, performs adversarial review, and assembles final deliverables.
2 6mo ago A 40 tokens
original MIT
dr-scout
04Agent
Performs wide-pass discovery for deep research runs. Searches the web using diverse queries, evaluates source candidates, captures metadata with credibility scoring, and writes structured notes.
2 6mo ago B 36 tokens
original MIT
dr-writer
05Agent
Synthesizes deep research findings into publication-quality reports. Reads all claims, evidence, and notes to produce coherent, evidence-backed narratives with explicit citations, uncertainty, and conflict documentation.
2 6mo ago A 40 tokens
original MIT
Hook
Runs when a task is marked completed, executing dr_audit.py via python3 with --mode. From Defiect/deep-research-plugin.
2 6mo ago A
tokens not measured
original MIT
TeammateIdle
07Hook
Runs on the TeammateIdle event, executing dr_audit.py via python3 with --mode. From Defiect/deep-research-plugin.
2 6mo ago A
tokens not measured
original MIT
PreCompact
08Hook
Runs before the context is compacted, executing dr_audit.py via python3 with --mode. From Defiect/deep-research-plugin.
2 6mo ago A
tokens not measured
original MIT
init
09Skill Claude CodeCodex
Bootstrap the deep research workspace directory structure and verify the environment is configured correctly.
2 6mo ago A 17 tokens
original MIT
report
10Skill Claude CodeCodex
Re-render the deep research report from existing artifacts without re-fetching sources. Useful for updating the report format or regenerating after manual edits to claims/evidence.
2 6mo ago A 34 tokens
original MIT
run
11Skill Claude CodeCodex
Run an end-to-end deep research workflow. Multi-agent orchestration with evidence tracking, triangulation, quality gates, and a final cited report.
2 6mo ago A 31 tokens
original MIT
status
12Skill Claude CodeCodex
Check the progress of the current or most recent deep research run. Shows stage, source counts, claim counts, and any issues.
2 6mo ago A 28 tokens
original MIT