Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for legal teams that already use Claude Code, Claude Cowork, or the Claude Managed Agents API and want a vetted, open-source starting point for practice-area plugins with built-in attorney-review guardrails, managed-agent cookbooks, and an extensible plugin marketplace.
Who should use it
Who should skip it
Consider anthropics/claude-for-legal lower priority if you already have a working solution in this category.
About this signal
anthropics/claude-for-legal is tracked by RepoRadar as a official anthropic plugins in the Agent Builders / Managed Agents section. It was first seen on 2026-07-02 and last updated on 2026-07-02. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for anthropics/claude-for-legal are workflow potential (9.9) and practical usefulness (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned anthropics/claude-for-legal a composite score of 8.4 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Outputs are explicitly drafts for attorney review and not legal advice; the README is unambiguous that a lawyer must verify, take professional responsibility for, and rely on the work product, not the plugin; Several agents route through third-party MCP connectors (Ironclad, DocuSign, iManage, Everlaw, CourtListener, Slack, Google Drive, Box) so users should confirm connector scope and access scopes before deploying on production matters; Managed-agent cookbooks schedule eyes-on-the-feed work and may need human-in-the-loop review for privilege and confidentiality before any filing or send.