Agent
Validates DOI, metadata, duplicates, OA status, and retraction. Receives a candidate list from search-scout, validates each paper, and updates the evidencematrix (§14.7).
11 1mo ago A 44 tokens
original MIT
11Stars on the repository
17Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
comms-writer
02Agent
Delegate when drafting research communications, summaries, or reports for a non-specialist audience. Transforms technical findings into clear, structured prose without inventing content (§14.7).
11 1mo ago A 40 tokens
original MIT
Agent
Delegate to own and advance the research tree — choose the best pending node to expand, prune branches by failure type, and record outcomes. Keeps tree-search state separate from the orchestrator.
11 1mo ago A 40 tokens
original MIT
Agent
Delegate when generating candidate research hypotheses for a topic — produces ranked, physics-grounded, falsifiable hypotheses with explicit AI-generated labels. Backs the maglab hypotheses command.
11 1mo ago A 40 tokens
original MIT
Agent
Pre-checks local notes and existing references for evidence and duplicates. Step 1 of research orchestration — queries the local corpus before a broad search to identify what is already held and what gaps remain (§14.7).
11 1mo ago A 50 tokens
original MIT
Agent
Reads 3–7 key papers in depth and extracts claims, evidence, and methodology. Targets T1·T2 papers verified by citation-auditor (§14.7).
11 1mo ago A 40 tokens
original MIT
Agent
Delegate when validating the physical plausibility of physics quantities, simulations, and fitting results via the sanity oracle. Checks dimensions, ranges, and conservation laws.
11 1mo ago A 33 tokens
original MIT
Agent
Delegate when a batch of measurement/simulation results needs to be digested in an isolated context and only compressed analysis conclusions should be returned.
11 1mo ago A 32 tokens
original MIT
search-scout
09Agent
Broadly collects candidate papers using MCP connectors and skills. Generates 3–6 query families and assigns tier classifications (§14.7).
11 1mo ago A 31 tokens
original MIT
Agent
Writes a topic-centred (not paper-by-paper) synthesis report. Receives paper-reviewer results and produces synthesis text with DOI evidence (§14.7).
11 1mo ago A 36 tokens
original MIT