Turns Claude Code into a rare-disease research workstation: phenotype-driven diagnosis, variant interpretation (ACMG), sequence-to-function models, genotype-to-therapy, classical statistics — every answer anchored to live public databases.
jev-governor
roma-vibe/jev-governor
Jev-guided model, effort and subagent routing for Claude Code (Opus 5.5 / Sonnet 5.5), auto-created specialist subagents and Jev-pruned compaction.
review-layers
seanjohnson-dev/review-layers
Layered code review for agent-written changes, the way the Claude Code team lands code: checks run first, a risk tier is set from the change, parallel bug hunters post only findings that verifiers confirm, security findings block, review rounds are capped, repeated lessons go into REVIEW.md, incidents become an eval, and git push / gh pr are gated until /land is green. Token-light: haiku by...
clean-view
eduardopicolli/claude-mods
Hides tool calls and shows a calm checklist above the prompt, in Dark Modern Soft colors
model-picker
juampymdd/claude-code-model-picker
A band above the prompt to pick which model, and which version of it, runs the next requests, with token, cache and usage-limit stats, an animated pane of charts and live agents for the whole session, and a tab where Claude notes the theory behind what it builds.
reading
enhki/claude-mods
A reading pane: Claude publishes documents, sections, issues and notes to read, you mark each read, acknowledged, agreed or to discuss with a comment, and the results go back as one message
walkthrough
enhki/claude-mods
A checklist pane for manual testing: Claude publishes the steps, you mark each pass, fail or skip with a note, and the results go back as one message
work-session
enhki/claude-mods
Kick off and wrap up working sessions with your start and end commands, and give each session a useful title
worksheet
enhki/claude-mods
A pane over a JSON worksheet: rows grouped by section with search and filters, your priority and comment per row beside Claude's proposal and reason, written straight back to the file, with tabs across the worksheets found and changes sent to Claude on demand or as they happen
opensearch-console
shohamtal/cc-mod-opensearch-console
OpenSearch & Elasticsearch Dev Tools-style console in a Claude Code side pane: Claude injects queries, you edit and run them (read-only).
mysql-client
shohamtal/cc-mod-mysql-client
MySQL client and SQL editor in a Claude Code side pane: Claude writes the query, you run it and see the results as a table. A database client with schema-aware autocomplete and a server menu. Read-only by default; writes run only after you approve them.
cockpit
Happykiller/claude-cockpit
Animated cockpit for Claude Code: live session activity (model, effort, mode, limits, context) and a timeline of the execution plan
agents-info
pazimor/marketplace
Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model and effort of each, tokens per agent × model × effort, 5 h / 7 day limits with forecast, alerts. Read-only: alters and blocks nothing.
sentinel
wellavelino/sentinel
A progress panel and band for the goal, every task and every subagent, and a highlighter pen for Claude's replies.
dot
curran-gehring/claude-dot
An always-on companion for Claude Code, after OpenAI's dots: a named avatar that keeps standing responsibilities, runs them on schedules in the background, does read-only proactive research, keeps notes you can read, and gates risky actions with Custom Rules and an independent Auto-review.
clean-view
faleiro-thiago/claude-skills-mods
A calm, friendly view: hides tool rows and shows one plain-English checklist above the prompt.
skins
faleiro-thiago/claude-skills-mods
Skins for Claude Code's transcript: themed tool rows, reply gutters and spinner words. /skin swaps them live.
ssh-tools
moxisuki/claude-ssh-tools
SSH hosts, commands, SFTP transfers and tunnels for Claude Code. Per-project and global host files, encrypted credentials, password/key/agent authentication, scanned config and one-command diagnostics.
assumption-tracker
robinade/claude-mods-ko
Claude가 작업하며 세운 가정을 기록해요. 옆 패널에서 맞음·틀림을 표시하면 정정이 Claude에게 전달돼요 (한국어판)
idea-shelf
robinade/claude-mods-ko
작업 중 떠오른 곁가지 아이디어를 /idea 로 선반에 올려 두고(Claude도 직접 올려요), 나중에 클릭 한 번으로 Claude에게 보내요
cc-codemod
darjss/claude-code-codemode
Code mode for Claude Code: one tool that runs a JavaScript script over Claude's own tools and returns only the answer
agentille
hasuwini77/agentille
One typed command runs the work: /agt plans, builds and reviews with the right model per step, steps aside on small tasks, and ends on one short card. Also typed-only: /storm picks what to build next, /agt-spawn and "open two sessions" open panes beside you, /agentille-init writes your voice profile, /agentille-project and /agentille-claude-md tend a CLAUDE.md; the /agt-* commands read or...
jev-router
DarkisuSu/Jev-Claude-Router
Routes skills and models with TypeSafe Jev and supplies automatic assistant-owned typed decisions throughout a task
learn-trail
UlongChaS2/learn-trail-mods
설명의 목차·현재 위치·곁가지를 패널에 띄우고, 항목별 설명을 저장해 /recall 로 그대로 다시 본다