6 tagged agentic-researcher, measured the same way as everything else here.
Skill Claude CodeCodex
Diagnose Soothe agent loops from /.soothe/logs (soothe.log, daemon.log, cli.log) and per-loop runner.log. Analyzes StrangeLoop plans, CoreAgent writetodos, tool-call anomalies, and skill loading. Use when debugging loop hangs, failed steps, TUI mismatches, wasteful plans/todos, or skills not loaded. For autopilot jobs…
Skill Claude CodeCodex
Inspect Soothe autopilot jobs: goal DAG structure, LoopRail conformance, parallelism scorecard, consensus/sendback, engine deadlock recovery, and goal execution history (jobloops attempts, wall times, phase timeline from railtrace). Use when the user names a job id, asks about rail/pool/DAG stuck goals, low…
foundry-works/foundry-research
Skill Claude CodeCodex
Part of foundry-research
Revision orchestrator that takes an existing research session and runs a structured review-then-revise cycle to improve accuracy, correctness, and clarity. Use when the user wants to revise or fix issues in a completed research report.
foundry-works/foundry-research
Skill Claude CodeCodex
Part of foundry-research
Deep research agent that searches academic databases, downloads sources, and produces structured evidence-backed reports. Use when the user asks for deep research, literature review, systematic investigation, or any question requiring multiple sources and synthesis.
foundry-works/foundry-research
Skill Claude CodeCodex
Part of foundry-research
Research quality evaluator that analyzes session artifacts and produces structured quality assessments with scores and recommendations. Use when the user asks to evaluate, reflect on, review, or score a completed deep-research session.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: