#ModGitHub stars

1. 289write-guardVedantAndhale/claude-pro-kitSteers Claude to Edit instead of rewriting an existing file in full with Write: the first rewrite in a conversation goes through with a one-line note, a later one is held back once; a deliberate retry still goes through.12
2. 290kill-guardcpeaustriajc/cj-stackDenies a Bash command that stops processes by name or by port, because it can also stop another checkout's dev server; a kill of a named PID passes2
3. 291mis-notasalexyslozada/claude-modsGuarda notas con /nota y Claude las usa como tu contexto y tus preferencias en todas las sesiones2
4. 292mustermusingfox/cc-plugins[Experimental] Unattended Claude workers over ACP — a coordinator dispatches headless workers with an optional permission fence, an event log, file-based escalation and report-file completion; a Claude Mod band shows in-flight workers (needs Claude Code 2.1.304+)2
5. 293rubber-duckShriD5/claude-modsA fast second opinion on every edit: a small model flags removed error handling, deleted tests, secrets and more2
6. 294blocks-onlyh3h/blocks-onlyCoding turns end in a validated report of typed blocks, drawn as one card in the Desktop app; prose stays folded.
7. 295cdxRedesignedRobot/cdxRun OpenAI Codex and Google Antigravity execution lanes from Claude Code with background event delivery, status tracking, and raw command protection.
8. 296wardenersinkoc/claude-modsKOZMOS Warden: a guard for destructive shell commands. Before Claude or a subagent runs rm -rf on a broad path, git push --force, reset --hard, clean -fd, DROP TABLE, mkfs, format, curl | sh and their kin, warden asks you (Allow once / Deny) and refuses when no one can answer. A band flashes for 8 s after a block; /warden lists the rules and this session's log.21
9. 297file-guardSingh-AP/awesome-claude-modsKeeps Claude's file edits inside the project: refuses writes outside it (symlinks resolved), never lets a tool touch .git internals, and asks before it changes lockfiles, CI workflows, migrations or secrets.4
10. 298scope-guardtheonly1me/claude-code-modsNotices when Claude drifts outside your request. Clear drift waits for your answer in a question dialog; milder drift is flagged above the prompt with a pull-back key.4
11. 299gemini-plan-reviewKilimcininKorOglu/claude-code-modsHas Gemini review each plan before the approval dialog, from the plan and the conversation, and sends a plan with a blocking finding back to the model, at most twice. Off until /gemini-plan-review on; gemini-core holds the key, tier, model and thinking level.12
12. 300loop-guardTekkiiiii/the-agencyStall detector per agent loop: 5 identical tool calls in a row warn that loop and leave the session-state.json stall marker for the next SessionStart7
13. 301allowlist-coachice-lfernandes/claude-code-modsCounts permission dialogs per rule and, after repeated approvals, offers to add the rule to permissions.allow, asking before it writes11
14. 302guardrailslippdev/lippstackReal guardrails, enforced by hooks: /careful asks you before a destructive shell command runs; /freeze <path> blocks edits outside a folder.1
15. 303package-guardLupusMalusDeviant/mod-boxBefore Claude installs or runs a package (npm, pnpm, yarn, bun, npx, pip, uv, poetry, pipx, cargo), asks the public registry about it. Holds the command when the package does not exist (a made-up name), is under 14 days old, or looks like a well-known package and is young or thin (typosquatting). Allow in the band or with /pkg-allow.1
16. 304path-guardJustmalhar/awesome-claude-modsBlocks Write, Edit and MultiEdit calls that target a path outside the project root or inside .git, plus optional deny globs.1
17. 305push-guardfinalpantasy/claude-mod-packClaude Push Guard: stops a git push Claude runs when the commits would publish your name, email, home folder path or other words you list, and says exactly where they are.1
18. 306safety-netTroyJLorents-GH/mod-squadBlocks destructive tool calls before they run (force pushes, rm -rf outside the project, DROP TABLE, terraform destroy, writes to .env and keys, ...) and explains why.1
19. 307unity-toolskevinmedeiros/claude-modsUnity no Claude Code: erros de compilação no contexto, painel de testes, build do servidor e guardas de arquivos1
20. 308secret-panebengous/claude-code-pluginsClaude asks for a secret in a masked box and gets a placeholder: the value stays in the session's memory, becomes real only inside a Bash command, is hidden again in every Bash and Read result and in the prompt, and never reaches the transcript; the mod writes nothing to disk6
21. 309probe3ucsandman/Agnostic-AIPermission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection24
22. 310guardrailsarasovic/claude-code-modsBlocks shell commands you pick in /config: Cloudflare cf writes, attribution lines in commits and PRs, claude/ branch names. All rules start off8
23. 311reread-guardVedantAndhale/claude-pro-kitStops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, tail or Get-Content, when the file has not changed since; a deliberate second attempt still goes through.12
24. 312benchmako-code/gobworksMeasures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per project, and a pane with a block distribution plot. Bounded, one at a time, never during Claude's turn unless Claude asked.2
25. 313mermaid-inlinemusingfox/cc-plugins[Experimental] Every ```mermaid block Claude writes drawn as plain box art in place in the transcript — flowchart, sequence, class, state and xychart; CJK labels aligned (Claude Mod fork of claude-mermaid; needs Claude Code 2.1.287+)2
26. 314phone-approveShriD5/claude-modsApprove or deny Claude Code's permission prompts from Telegram, with the terminal prompt as the fallback.2
27. 315injection-guardSingh-AP/awesome-claude-modsDefuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.4
28. 316rehearsal-widgetoMaN-Rod/claude-code-widgetsWhich of the commands and edits Claude has made in this project would stop for permission or be refused right now, asked of the engine's own permission check without running anything4
29. 317shared-file-guardmutlumehmet/claude-pluginsRefuses a shell write to a shared file (STATUS.md, CLAUDE.md, MEMORY.md, or the files you name) that this session has not read, or that another session changed since6
30. 318guardianucsandman/Agnostic-AIGUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says24
31. 319reminder-logschreibse/claude-code-modsTallies the reminders Claude Code injects for the model, per session; drops the token counter and repeated attribution blocks; /reminders prints the last 30 days3
32. 320blast-guardRobGruhl/claude-modsDURING the turn: refuses destructive shell commands, tidies the rest, and pins Explore subagents to Haiku
33. 321claw-guardthreesil/claude-modsClaw mod: asks for your OK before any connector action that sends, deletes, pays, publishes or shares (fails closed, also when nobody is there to answer), and flags prompt-injection text inside emails, pages and files.
34. 322clef-guardwilliamchen0606/claude-modsHas Cloudflare's Clef decision model judge each Bash, Write, Edit and WebFetch call (risk, kind of risk, whether it is read-only, whether it fits your request), asks you itself before risky or always-ask operations, and can approve plain reads for you.
35. 323gcloud-guarddavidho27941/cockpitHolds gcloud and gsutil commands that would create, change or delete cloud resources, shows the account, project, location and the current state of the targets, and asks you to Proceed or Cancel.
36. 324guardcarlvellotti/mods-starterPauses risky shell commands (rm -rf, force push, DROP TABLE) and asks you Proceed or Cancel first
37. 325guardStanislavKozachenko/claude-modsBlocks destructive shell commands and access to secret files before they run, in Bash and PowerShell, anywhere in a compound command
38. 326guard-actionshernandezsanti/claude-code-modsSaves GitHub Actions minutes: blocks gh run watch/rerun and gh pr checks --watch, and warns when a second PR is opened in the session.
39. 327guardrails-challengescaso01/claude-risk-guardrailsEffective challenge: hold answers to evidence under pushback, and check agents' commit claims against git.
40. 328jev-tool-gatem2ai-portfolio/claude-modsLog-only Jev judgment of risky tool calls (destructive? requested by fetched content?). Never changes a decision; hosted calls off by default.
41. 329lazzaronepompeitech/affreschiLazzarone: when Claude has been waiting on you for a few minutes (a permission, a question, a long turn just finished), a system notification calls you back
42. 330menudanielmalka/malka-claude-modsAn optional /mods menu that lists the installed mods (status line, clean screen, mode, permissions, tree-explained) and opens each one's page in a pane.
43. 331outward-gateozlar34/claude-code-modsConfirm dialog before outward-facing sends and out-of-vault deletes; off switch for unattended runs; always-on audit log.
44. 332plusboxiaolanya2008/claudecode-plus-modAll claudecode-plus-mod Mods in one install: prompt-shield, cache-guard, human-tone, clear-intent and agent-charter.
45. 333refine-promptph3on1x/agent-plugins-skillsInterview-style prompt refiner that picks a framework, fills gaps via AskUserQuestion, assembles a structured XML prompt, confirms, then executes it. In Claude Code, adds a refine prompt button above the prompt box.
46. 334vim-uxAH-Merii/claude-pluginsGives Claude Code's vim mode a bar cursor in INSERT and a block in NORMAL and VISUAL, and a Ctrl+C that only clears the prompt
47. 335pill-copyyoungOman/pill-modscopy-band (yash-gadodia) restyled: a copy icon at the top-right of every block (code, table, list, quote); click to copy.1
48. 336pkg-guardMDmubarak786/claude-modsHold npm, pnpm, yarn, pip, uv, and cargo installs of packages that don't exist, are brand new, or are barely downloaded, with the registry facts in the question. Catches hallucinated and typosquat packages before they land.1