#ModGitHub stars

1. 193ask-choicei-noma-ru/claude-ask-choiceWhen a reply ends with a choice-based question written in plain text, has the model re-ask it with the AskUserQuestion picker so you can select an option instead of typing.
2. 194ask-notchsameeeeeeep/ask-notchClaude's questions drop from your Mac's notch as a card. Click an option, pick with 1-4, type your own answer, or press esc to answer in Claude Code as usual.
3. 195auto-checksonata39-star/claude-modRuns the project's linter after each edit and its type-checker before Claude stops, handing failures back to Claude
4. 196auto-levelZiggedy/claude-auto-levelWählt pro Prompt automatisch Modell (Sonnet/Opus) und Denktiefe anhand von Stichwort-Regeln.
5. 197auto-session-titlefernandokobayashi-telus/claude-modsTitles the session after a few prompts and refreshes it as the work drifts; /done and /undone add or remove a checkmark in front of the title.
6. 198away-keep-runningiosifnicolae2/claude-away-keep-running/away turns your Mac's screens off while the Mac stays awake, so Claude Code keeps working while you're gone. Move the mouse or press a key to come back.
7. 199bangdrnic/claude-modsRun ! shell commands sent from Remote Control, and /run the last ! command Claude suggested
8. 200better-compactionspiiritual/claude-code-stuffCompaction that waits for the model's turn to end, and summarizes at its own effort level.
9. 201bismillahkavunkarpuz-debug/miscicKullanıcının her prompt'una verilen cevabı ayarlanabilir bir açılış satırıyla başlatır (varsayılan: Bismillahirrahmanirrahim)
10. 202browser-boostRukono/browser-boostMakes Claude drive browsers faster: a browsing playbook, smaller default screenshots, and nudges to batch actions.
11. 203calmjoshhornby/dotfilesHide tool noise and show one live status line while Claude works. Needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.
12. 204cc-code-format-modkukaka/cc-modsRewrites every fenced code block in an LLM response so it conforms to the language's standard style (Prettier for the web stack, black for Python, gofmt / rustfmt / shfmt where installed).
13. 205cc-glm-web-searchczpGhost/cc-glm-web-searchZ.AI (GLM) web search and web reader for Claude Code, authenticated by a Z.AI email (OAuth) login instead of an API key.
14. 206cc-mod-suggestion-sentence-caseVatroslav/cc-mod-suggestion-sentence-caseThe dim prompt suggestion that Tab accepts starts with a capital letter and ends with a full stop, unless it is a slash command or already ends a sentence
15. 207change-of-subjectjambolo/claude-modsJudges every prompt against the session it was typed into: offers /btw for one that belongs to another subject, and a fresh session or a compaction for one that starts a new phase.
16. 208chartsThomasTartrau/chartsDessine les blocs vega-lite, mermaid et dot des réponses en vraies images (PNG dans Ghostty, SVG sur le desktop).
17. 209chat-timestampsCaptainPalapa/palapa-claude-modsStamps each prompt and reply with the time it landed, each reply with its gap and time into the turn, and the turn's last reply with the turn's total.
18. 210chrome-closeAnnihilationWizard/chrome-closeAllow one headless Chrome at a time: refuse Claude's launches while any headless Chrome or its leftover helpers still run
19. 211claw-heartbeatthreesil/claude-modsClaw mod: wakes Claw up on a schedule inside a running Claude Code session. Daily briefing at a set time, periodic checks for overdue tasks, quiet hours, and an optional auto-run mode that makes Claude do the heartbeat by itself.
20. 212clef-gatedwain-barnes/clef-gateAsks a local Clef decision model whether an expensive tool call or subagent is actually needed before Claude Code pays for it. Logs every decision; shadow mode by default.
21. 213clef-model-routerdwain-barnes/clef-model-routerPicks the Claude model and reasoning effort for each turn with Cloudflare Clef, a fast decision model, on Workers AI or fully local (llama-server, Ollama).
22. 214clef-verifywilliamchen0606/claude-modsBefore Claude ends a turn that changed files, has Cloudflare's Clairic extraction model read the command output and the Clef decision model check that the work is shown to be done (tests run and passing where needed, claims backed by the steps, nothing asked for left undone), and sends Claude back if not.
23. 215clip-commandi-noma-ru/claude-clip-commandWhen a reply contains a command for you to run (a code block starting with "! "), copies it to the clipboard and places it in the empty prompt input. Pressing Enter on that exact text runs it and sends the output back to the model.
24. 216code-rundanielboston38/code-runStatus line: progress of the newest long-running job log (count and time left only, never its output)
25. 217collapse-tools0xnicholasy/claude-mod-collapse-toolsClaude Fold: Collapses each tool call to one clickable line in a color you pick, showing the model's own description of the call where it has one.
26. 218compact-tailGooner44/ClaudeModsAutomatic compaction summarizes only the older part of the conversation and keeps the latest part word for word; a reopen tool brings back anything summarized, from a local archive
27. 219connection-badgefiliptaka/connection-badgeShows in the prompt footer whether the session runs locally or over SSH, and on which server
28. 220converterzrdqns/claude-code-converterConverts PDF, Word, Excel and PowerPoint files to Markdown with markitdown before reading them
29. 221copy-buttonGeckoKing9/claude-code-copy-buttonCtrl+click copy link on every code block in Claude's replies (normal mode; WSL + Windows Terminal, Linux desktops, nothing to install)
30. 222copy-codejohnlewczuk/claude-modsAdds a hover-revealed copy button to each code block in assistant replies (fullscreen terminal)
31. 223copy-markdowna-bine/claude-modsA small copy control on each reply that copies the whole reply as its original markdown, plus /copy-md [n]
32. 224correction-ledgerCoderDayton/vii-modsSaves each correction you make as a rule, sends it every turn or when Claude makes the call it is about, makes it louder each time it is broken, and removes it when it is no longer used.
33. 225cyskoenvdheide/cysTracks the temporary files Claude creates and asks it to clean them up at the end of each turn.
34. 226day-logluba-hub/claude-modsA written log of your day with Claude: what you asked, when, and how long each took. Saved to ~/claude-day-log/.
35. 227docs-firstnuko-nova-dynamics/docs-firstHolds back dependency changes, new imports and sensitive-file edits until the session has checked the registry or the official docs for them.
36. 228done-gateJvrd97/claude-done-gateClaude cannot say "done" while the tests fail: a Stop gate runs your test command after every turn that changed files, and existing test files are locked so they cannot be patched green.
37. 229effort-routertotally-tim/effort-routerPicks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or a compatible service) and shows the level on the spinner and on the line that closes the turn. In shadow mode it shows and logs its pick and sends the session's effort; in enforce mode it sends the pick. Requires CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.
38. 230erp-log-nudgeUsamaSadiq/claude-modsReminds you late on weekdays to log your ERP time when today is still empty, pointing at /generate-erp-logs
39. 231escudoGuillermoAlbert/claude-modsOculta a Claude los datos personales (DNI, NIE, IBAN, teléfonos, emails, claves) cambiándolos por falsos válidos y los restaura al ejecutar, todo en tu máquina
40. 232event-bridgeseanrobertwright/claude-mod-eventsSends session, turn, attention and tool events to a host program over HTTP and, when allowed, takes prompts and interrupts back.
41. 233evolver-modsEvoMap/evolver-claude-code-modsEvolver for Claude Code as function hooks: recalls one EvoMap strategy per prompt, reports each reuse with the evidence the turn produced, and distills verified work outside the conversation. Nothing but the recalled steps enters the model's context.
42. 234exam-gateswei99386-alt/exam-gateBefore Claude calls a task done, run your checklist. Fail means Claude is sent back to fix it; repeated failure trips a breaker and hands control back to you.
43. 235explainDavid-AP-TON618/claude-explainRe-render an answer one rung up: controlled language (STE), a diagram, a self-contained interactive HTML page, or a narrated explainer video. /explain <ste|diagram|page|video> [subject]
44. 236ext-agentdarkautism/ext-agentRun Claude Code subagents in pi or opencode instead of a Claude model. Adds the ext-agent:worker agent type; built-in subagents stay available unless you opt in to blocking them.
45. 237fix-on-editonk3sh/fix-on-editRuns your project's linter on each file Claude edits and feeds any errors back so Claude fixes them in the same turn.
46. 238fmcsmoot99/MafiosoFirstmate 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.
47. 239fmsKeLe100/firstmateFirstmate 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.
48. 240forgesudikama/forgeContinuous engineering loop for Claude Code: Jev-based size/clarity triage, a plan-clarify-build-test-revise harness for small tasks, and for large tasks goal+spec from Jira/Docs/PDF/PRD/Figma, codebase scope validation, detailed clarify (incl. subagent count without file collisions), spec lock, an autoresearch-style ratchet loop with an orchestrator, worktree lanes and a deterministic judge (happy/unhappy/edge/regression), BLOCKED findings, final report, and per-repo self-learning.