#ModGitHub stars

1. 97mod-packaz9713/claude-mod-packA pack of small Claude Code mods that share the band above the prompt without overwriting each other. Turn each one on or off with /mods.9
2. 98recap-plusskanehira/claude-recap-plusKeeps a recap-plus summary of the session above the prompt: what it is for and where it stands; /recap-plus adds what was done and decided, what waits on you, and what comes next9
3. 99roadraven-hudShuffzord/RoadRavenRoadRaven pane in Claude Code: live agents on roadmap nodes, batched UAT sign-off, and a backlog you can start or prioritise9
4. 100taxi-speedcamdevbrother2024/devbrothers-mods위험한 Bash 명령 앞의 과속 단속 카메라: force push·rm -rf·DB 삭제·변경 폐기·운영 배포를 찰칵 잡아 [가주세요]/[세워주세요]로 묻습니다9
5. 101hal-grammar-checkvinta/hal-9000Grammar-check your prompt as you type, shown above the prompt box142
6. 102coa-deskdavebream/claude-of-alexandriaOptional study-desk extras for the coa plugin: see which data lookups grounded an answer and read a passage beside the conversation. Terminal and desktop app only.8
7. 103desk-asanaKyongSik-Yoon/cc-desktop-modClaude Code mod that opens your Asana tasks in a side pane (/desk-asana): the tasks assigned to you, a search across the workspace and your projects' tasks by section, with details, comments, adding a comment, assignee, dropdown fields and status. Reads Asana through the Asana MCP server Claude Code already has connected. Pairs with desk-look8
8. 104glanceflowAntreas-Strb/glanceflowGlanceFlow: see what Claude is doing, at a glance. Hides tool rows and shows one plain-English checklist above the prompt, with progress, helpers, history, a team report, pause and continue, and a password guard.8
9. 105prompt-polishjheroorehj/prompt-polishPolishes your prompt for the model before you send it, and shows it next to the original8
10. 106agent-flowluucas42/agent-flowA live workflow panel: the main model, the advisor and every spawned agent as cards joined by arrows7
11. 107asideJayDoubleu/asideRead-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answers come from a tool-less fork of the session's own transcript and nothing is written back into the main thread.7
12. 108redgreenhellosverre/redgreenTest results pane for Claude Code: every test run Claude makes becomes a pass/fail list with the failure detail and run history. vitest, jest, pytest, cargo, go, bun, deno7
13. 109afkswitchaugbastos/afkswitchAFKSwitch by augbastos — Tell your agents when you're away and when you're back.2
14. 110claudinatorpatheonsceo/claudinatorGive Claude Code a glow-up: six switchable looks and nine mixable ingredients for tool calls, the working line and turn receipts, plus panes to navigate long sessions. Draws locally, makes no network requests.2
15. 111agents-panelBoom-Vitt/boombignose-modsSide pane listing project, user and plugin agents with a run button each; /agents-panel toggles it.6
16. 112batonashishsk93/baton-modsPass tasks between named Claude Code sessions: the receiver queues them, works each to a pull request, reports back and picks up the next. A band and panel show your sessions and tasks.6
17. 113brickfallreporails/arcadeA brick breaker in a Claude Code pane, after Arkanoid: steer with the mouse, catch capsules, chain volt bricks, over a shimmering iridescent field. A real picture in kitty and Ghostty, block characters elsewhere.6
18. 114clawdhouseishuagrawal/clawdhouseA pixel Clawd in a side pane that reacts to what Claude is doing6
19. 115goblin-chromeJasonWarrenUK/goblin-modeGoblin-mode's face inside Claude Code: a goblin in the band that reacts to the session and holds a prop for the skill that runs, minions for the subagents out, spinner words per skill, hint lines in its voice, a mask over every question, frames by model tier, a day cycle and the project theme's colours.6
20. 116kgai-modkgaidev/kgaiExperimental kgai add-on for Claude Code with function hooks: checks each code-editing turn for a structural decision on the side, records it without a line in the transcript, and draws kgai's own tool calls as one line each. Requires the kgai plugin.6
21. 117mission-controlJasonWarrenUK/goblin-modeCoordinate several Claude Code sessions on one repository: a ledger of shared-resource slots enforced by hooks, a /mc board pane, tools that report, request, grant and broadcast, a kick-off that writes each session's brief, and the protocol that came out of running it.6
22. 118rllvmh1994st/rllvmCapture LLVM bitcode from any build and query it through rllvm-query's MCP server.6
23. 119skywardgabfssilva/skywardSkyward for Claude Code: the `/sky` panel over the daemon's computes, an MCP server (`sky mcp`) whose tools read and operate them, and a skill for the Python SDK, the `sky` CLI and scripts run with `sky run`.6
24. 120sleightLand-o-Clusters/sleightUnofficial: lets Claude drive macOS apps in the background through the computer-use engine bundled with the ChatGPT desktop app, without taking over your cursor.6
25. 121time-blamekaranb192/time-blameSplits each Claude Code turn's time into Claude, tools, you and other, and prints a /blame receipt for the session. Nothing leaves the machine. Claude Code 2.1.302+.6
26. 122assumption-trackerYeonwooSung/my-claude-code-modsAssumption Tracker1.1k
27. 123clawd-madenciselmakcby/clawd-madenciClaude çalışırken istemin üstünde piksel Minecraft sahnesi: Clawd kazar, inşa eder, TNT patlatır5
28. 124conversation-atlasNeelAPatel/Claude-Mod-ConversationAtlasA live side pane that maps a long Claude Code session: goal, current path, possible detours, decisions, open questions, checkpoints, working files and what to resume next. It observes on its own and asks before changing your intent.5
29. 125devcycleKonstantinRoehrl/devcycleOpinionated pipeline from a feature, bug, or refactor description to a verified, publish-ready implementation: scoped interview, wave-based plan, parallelized subagent execution, cross-model branch review, on-device UI verification via claude-in-chrome, and GitHub reconcile — layered on the superpowers skill set, with a doctor/learn loop that benchmarks and improves the pipeline from session to session.5
30. 126image-previewJonasR-Git/claude-image-previewSee the pictures in your prompt: thumbnails above the prompt for pastes, @-mentioned files and the clipboard, with the real picture laid over them on Windows, plus a gallery and clipboard paste and copy. Windows, macOS, Linux and WSL.5
31. 127katharsisOpenScribbler/KatharsisAn output style that classifies each message by exchange type and shapes the reply to fit it: the answer first, a ceiling per type, reference codes that survive the session, and decisions handed back as questions5
32. 128litclaudewjgoarxiv/litclaudeClaude Code-native workflow plugin with a bounded-authority start-work lifecycle.5
33. 129mods-image-previewhahmjuntae/claude-mods-image-previewShows thumbnails of pasted images above the prompt, in any terminal5
34. 130my-modtomada1114/tomada-claude-pluginsA band above the prompt. Replace with what your mod actually does.5
35. 131pokemonJinHang02/claude-code-pokemonYour Pokémon party journeys through a pixel world above the Claude Code prompt: it runs while Claude works, cheers when tests pass, faints when they fail, levels up and evolves.5
36. 132prompt-queuegalElmalah/claude-modsA prompt typed while Claude is working is held in a stack above the prompt instead of landing in the running turn, and sent once the turn ends. Reorder the stack, edit a row in place, send one first, remove one, flush the lot. Needs function hooks (early access) and an interactive terminal.5
37. 133reflect-modpartalemre/MODZclaude-reflect as a Claude Code mod: a cheap trigger-word prefilter (Turkish and English) and one model check find reusable corrections; a card above the prompt saves them to the chosen CLAUDE.md; /mine finds friction that repeats across past chats and proposes rules, hooks, skills or mods5
38. 134review-paner3al1tym/claude-reviewclaude review: the session's latest reply in a calm reading pane docked beside the conversation, with its plan, question and tasks one key away5
39. 135vibehausrmguney/vibehausA cozy pixel house for your Claude Code agents: the lead, subagents and background tasks from every session as a Clawd household in an autumn garden, with hover cards, and a vibe fatigue band of your plan usage above the prompt.5
40. 136whiteboard-defenseavestura/whiteboard-defenseAfter substantial work, tells you what you should know to defend it at a whiteboard: the decisions, who made each one, and where the agent relied on its defaults.5
41. 137prompt-enhanceryonatangross/orchestkitReview enhanced prompts before sending them: short, stack-aware rewrites300
42. 138ai-sdlcSennjen/claude-sdlcHook-enforced approval gates for Claude Code: intent → spec → plan → build → verify → review, with a status bar and one-click approvals.4
43. 139ai-skillsBenjaminG/ai-skillsBenjamin's collection of Claude Code skills — daily workflow, code quality, dev tools, and specialist agents.4
44. 140archpanefacumarcet/archpaneLive architecture diagram in a side pane that Claude draws and edits while you talk4
45. 141cairnjmgirard/cairnMilestone-driven development workflow and tracking system for Claude Code projects: a language-agnostic core with per-repo toolchain profiles (R, Python, Claude Code plugin, Quarto extension, Docker image, or generic), plan/implement/review skills, hotfix and release paths, Fable review briefs, and a self-auditing cairn/ file system.4
46. 142capability-composerdichotomouskeyz/capability-composer/capabilities <task>: finds the skills, plugins, tools and web discoveries that would do the work better, shown as a pixel-art upgrade screen4
47. 143catalog-paneT-AI-Labs/claude-code-modsA pane, opened with /catalog, that lists every skill, command, agent, mod, plugin, settings hook, MCP server and tool by category: descriptions, usage over 7 and 30 days, token cost, what each mod hooks, updates, GitHub stars, a model-written note on what each is for, and buttons to insert, run, update, disable or uninstall.4
48. 144clawd-talesplaxagoras/clawd-talesA pixel Clawd acts out every tool call above the prompt; helpers wander in by model color. Terminal-first, no model calls.4