#ModGitHub stars

1. 145compact-jevedoproch/compact-jev/compact-jev: Jev-guided verbatim compaction for Claude Code, called through Vercel AI Gateway. Never replaces /compact or auto-compaction.1
2. 146decision-compactionzchee/claude-code-modsHands back the conversation itself in place of a compaction summary, less the tool calls and results a System One decision model judges no longer needed. The model can be TypeSafe Jev, Cloudflare Clef, Codiv OpenJev, Perplexity pplx-decider, OpenAI GPT-6 Luna, or Jev through OpenRouter, decisions-api.dev or decisionapi.net.1
3. 147effort-live-controlrezzminator/effort-live-controlSet each Claude Code sub-agent's reasoning effort per spawn with [effort: low|medium|high|xhigh|max], and let an opted-in agent's effort rise at each failing test run or red sub-task and come home once the trouble resolves.1
4. 148explore-modelrlorenzo/ai-coding-setupPins the model that background recon subagents run on. An agent.spawn hook sets the Explore subagent's model to haiku, so a session driven by an expensive model stops billing its codebase searches at that tier, without shadowing the built-in agent definition and without the CLAUDE.md load a replacement definition would cost.1
5. 149fmlmuehleisen/xoFirstmate Calm for Claude Code: the sailboat working animation and conversation-only transcript presentation, sharing the per-home config/calm preference with the Pi Calm extension. Its hooks module may load through CLAUDE_CODE_ENABLE_FUNCTION_HOOKS or Claude Code's tengu_plugin_hooks_modules rollout flag, but the mod activates only when CLAUDE_CODE_ENABLE_FUNCTION_HOOKS is exactly 1 and is otherwise a complete no-op.1
6. 150gateway-switchzchee/claude-code-modsSwitches a running session between api.anthropic.com and the local Model Gateway: onto the gateway once Remote Control has registered, on /gateway on, or as each session starts after /gateway setup, and back to api.anthropic.com whenever the gateway stops answering.1
7. 151gui-editorssandipchitale/gui-editorRich GUI editors for plugins/marketplaces (/plugin-editor) and MCP servers (/mcp-editor) in a Chrome app window, served by a local server tied to the mod's life.1
8. 152inline-imagesMechazawa/claude-inline-imagesGives Claude a show_image tool and shows pasted images and images Claude reads inline in the terminal transcript1
9. 153jev-governorroma-vibe/jev-governorJev-guided model, effort and subagent routing for Claude Code (Opus 5.5 / Sonnet 5.5), auto-created specialist subagents and Jev-pruned compaction.1
10. 154jev-model-routerDmitryBMsk/thinkdialPicks the model and reasoning effort for each task with TypeSafe's Jev. Routes subagent models at agent.spawn and subagent and main-loop effort at turn.step, with optional main-loop model routing. Falls back to the engine's built-in classifier when no key is set.1
11. 155jev-model-routerKiy-K/oxidePicks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.1
12. 156jev-routedrewpayment/jev-routeRoutes each turn to the cheapest capable Claude model using Jev, TypeSafe's decision model. Toggle with /route.1
13. 157jev-routerHoppin-Sorter/jev-routerAsks Jev before each prompt what the task is and how hard it is, then picks the Claude model (and optionally effort) and the skill that fit. /jev and the Jev Bar menu bar widget set the quality/cost focus.1
14. 158jev-skill-scoutkaranb192/jev-skill-scoutBefore each prompt reaches the model, TypeSafe's Jev ranks your installed skills against it and attaches one line naming the skill to load. Sends the prompt text to api.typesafe.ai. Needs function hooks (early access).1
15. 159jevshiftunclecode/jevshiftExperimental Jev-assisted model and effort selection for Claude Code: observe, pin, off, and opt-in auto.1
16. 160loc-todaypepperonas/loc-todayToday's lines of code by Claude, across all sessions, under the prompt: new, edited and deleted lines, and on hover the split by project, largest first1
17. 161mermaid-renderejklock/claude-mermaid-renderRenders the Mermaid diagrams Claude Code writes or reads as elegant cards in the transcript: colored Unicode art in any terminal, real SVG on desktop.1
18. 162message-timestampsbenjaminmodayil/live-recapPrefixes each Claude reply in the transcript with the local time it arrived, with no model calls1
19. 163model-tagyyosifov/prompt-modsPer-message model and effort: put @haiku or @max anywhere in a prompt and that one turn runs on it1
20. 164nowloadingvgnshiyer/nowloadingThe line that animates while Claude works, redrawn as something from before: tape decks, departure boards, an hourglass, a floppy drive, a dot-matrix printer, an arcade rally, a filmstrip, and a pixel campfire.1
21. 165open-in-vscodegggg5151/claude-desktop-links-to-vscode-modClicking a file reference in a desktop reply opens it in VS Code at the line (Remote-SSH or local).1
22. 166open-linkshelenkwok/open-linksA Claude Code mod: file paths in Claude's replies become links that open the file (or your editor at the line). macOS, Linux and Windows paths, relative ones resolved against the session folder.1
23. 167preallowEntwining/modsLets Claude Code auto mode run the steps of the task you gave without the classifier: a model judge allows what is reversible or what you explicitly asked for1
24. 168prompt-navAJclemendor/my-modsPrev chat and Next chat buttons that jump between your prompts and leave the transcript still at its end.1
25. 169read-stubalex4o/system-one-modsOn a full Read of a big source file, a System One model (Jev, or the open-source decider) decides per function/method/const whether to include it; the rest become stubs.1
26. 170rice-multi-modelsmoabualruz/rice-multi-modelsCodex (ChatGPT subscription), OpenCode Zen and Go, and configured API or local providers as session and subagent models, no proxy1
27. 171rtl-textaliir74/claude-code-rtlShapes and reorders Persian, Arabic and Hebrew text in the transcript through fribidi so the terminal draws it joined, right-to-left and right-aligned.1
28. 172self-compactkzarzycki/claude-modsCompaction at task boundaries: the model can ask to compact once its turn ends. Above a fill threshold it is asked whether to, after a turn decision-model judges a finished task, or, without decision-model, with each prompt.1
29. 173semantic-grepalex4o/system-one-modsA 'search' tool: ranks every function (or file) under a glob by a System One model (Jev, or the open-source decider) against a plain-language query.1
30. 174stepwardengetexcited/stepwardenEvery tool call your agent makes, checked before it runs. Verifies each pending tool call against the session's plan using TypeSafe AI's Jev model, then allows it, asks you, or blocks it.1
31. 175switchboard-notchsameeeeeeep/switchboard-notchClaude's questions drop from your Mac's notch as a native card. Pick with 1-4, type your own answer, or press esc to answer in Claude Code as usual.1
32. 176tab-tagJCPetrelli/tab-tagNames the iTerm2 tab with one or two uppercase words for what the session is about, and gives each session's tab a random colour.1
33. 177task-plannerGorossy/task-plannerRecomienda modelo, effort y subagentes al empezar una tarea nueva y aplica la eleccion en silencio.1
34. 178willowyha9806/wishing-willowShows how the model decoded your request, next to your verbatim prompt. It never judges whether they agree — you do.1
35. 179jev-gateMongLong0214/jev-gateJev Gate in one plugin: the orchestration gate, the extractive compactor and the Jev effort and model router. Every part is on by default; each has its own on/off option.4
36. 180jev-gate-routerMongLong0214/jev-gateRoutes the main thread's effort and each subagent's model and effort with one TypeSafe Jev assessment; on by default, native on any doubt.4
37. 181review-queueYeonwooSung/my-claude-code-modsReview Queue1.1k
38. 182use-haikumidudev/better-claudeStart a prompt with _ and that turn runs on Haiku, shown as you type, while it runs and under the answer.240
39. 183herdrbendrucker/claudeDrive the herdr terminal workspace manager: panes, tabs, workspaces, and sibling coding agents18
40. 184quick-peekmidudev/better-claudeThe paths in Claude's replies become links: hover one to preview it, click it to show it in Finder.240
41. 185absolutely-notJvrd97/claude-absolutely-notStop "You're absolutely right!": a tone rule in the system prompt, praise openers stripped from what the model reads back, and /tics to count the ones that still get through.
42. 186agent-autopilotapolenkov/agent-autopilotAnswers AskUserQuestion polls for you only when the assistant marked one option (Recommended) and nothing looks irreversible; default is a hint.
43. 187agent-coloursMadAppGang/magus-alphaColours subagent and skill names in Claude Code by their own color: field. An agent's name sits on a coloured badge in its Agent row and in replies; a skill's name is drawn in its colour in its Skill row and in replies. Alpha: a function-hooks mod; it ships no commands or skills of its own.
44. 188agent-model-badgeNew-Retr0/claude-dockShows each spawned subagent's resolved model and effort beside its row, so a surprise model assignment is visible at a glance.
45. 189agent-model-routerlideke/agent-model-routerPicks the model each subagent runs on from a per-project table, steps up a model when a task is retried, and logs every choice so an agent can tune the table.
46. 190agent-skillsfive82/claude-modsLoads skills from the cross-harness .agents/skills directories (project and ~) into Claude Code: listed for the model and runnable as /<skill>.
47. 191answerPeteChu/cc-answer/answer: answer the questions in Claude's last reply in Claude Code's native question dialog
48. 192anymodelph3on1x/agent-plugins-skillsClaude Code subagents on the models you choose: name as many agents as you like, each on a model from your own providers (LM Studio, Unsloth Studio, llama.cpp, vLLM, OpenRouter, any Anthropic-compatible API), and call them like Claude's own subagents while the main session stays on Claude.