backlink-manager
Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.
Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3 iterations.
> /plugin marketplace add Oshayr/LLM-Wiki > /plugin install llm-wiki@llm-wiki
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3 iterations.
name: research-loop description: "Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3 iterations." model: sonnet
Run an autonomous research loop: generate hypotheses, search, ingest to wiki, evaluate quality, keep or discard via checkpoint. Max 3 iterations by default. Stops on metric plateau or question saturation.
Resolve `.wiki/` from plugin install scope. Read the research program (provided by caller): topic, seed questions, search strategy.
Create a checkpoint of current `.wiki/` state as a rollback point.
From the program's seed questions and any remaining open questions from `.wiki/overview.md`:
Launch `search-orchestrator` with the queries. Receive ranked, deduplicated results.
For each top result: launch `wiki-writer` (mode: ingest) to compile into wiki pages.
After ingestion, assess:
After the loop completes:
An autonomous knowledge base that grows as you work. LLM Wiki is a Claude Code plugin that captures research, ideas, and decisions into an interlinked wiki with semantic search, automatic research, and a Wikipedia-style web UI.
Repo: Oshayr/LLM-Wiki
Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.
Explore citation chains for a topic. Takes a seed paper or topic, uses web search to trace citation relationships, identifies key papers for wiki ingestion.
Verify factual claims in wiki pages against external sources. Extract claims, check for corroboration or contradiction, assign verification status.
Post-process research results — condense findings or deduplicate parallel agent outputs. Two modes.
Parameterized search channel — web, academic, code, docs, or wikipedia. Returns normalized result arrays.
Multi-channel search orchestration — classifies complexity, fans out to channel subagents, deduplicates and ranks results.