#ModGitHub stars

1. 49session-handoff-buttongclbck-crealore/session-handoff-button-modA Session Hand-off button above the prompt, colored by context usage; reads Context clean and cannot be pressed while green. From orange on, one press writes the handoff, saves it to a temp .md, clears the session and continues in the fresh one with a short message while the handoff goes in as hidden context. Past 65% it stops your next prompt once and recommends the button.2
2. 50watchdogmatteoantoci/claude-code-watchdogWatchdog agents review each update of the agent you work with and push short notes to it. It spawns review subagents and auto-allows only its own review spawn and reviewer reads of files the main agent already read.2
3. 51exit-memory-updatemanueldelgado/manueldelgado-modsBefore /exit, offers to update CLAUDE.md with the session's learnings (via claude-md-management when installed).
4. 52anon-modeeveiljuice/claude-anonclaude anon — incognito mode: clean context (memory, CLAUDE.md, history unloaded), session not saved, transcript deleted at exit1
5. 53auto-handoffAkash001uts/claude-modsHands a long session off cleanly: at a context threshold Claude updates the docs and writes a handoff, the session compacts with its instructions, then a kickoff prompt carries on. Gives Claude a live context reading and a /wrap-up skill1
6. 54auto-handoffSpardutti/claude-modsHands the work to a fresh, named session when the context gets too full, using your /handoff command1
7. 55breadcrumbscrockalet/claude-modsA pane beside the session that Claude talks to you through: the task, what it is doing, the notes it files, the questions it went on without, and manual tests you run when you get to them.1
8. 56code-modernizationbadaniya/.stowedGuided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).1
9. 57compact-methodskzarzycki/claude-modsoh-my-pi compaction methods: shake (move old tool output to files, no model call) and handoff (continue from a handoff document). Use `/compact shake` or `/compact handoff [focus]`.1
10. 58context-handoffAkash001uts/claude-modsHands a long session off cleanly: at a context threshold Claude updates the docs and writes a handoff, the session compacts with its instructions, then a kickoff prompt carries on. Gives Claude a live context reading and a /wrap-up skill1
11. 59ctx-relaymangow314/mango-modsHands off before the context fills up. Past the handoff line it counts down 60 s, writes a handoff file with a fork, runs /clear and resumes in the new conversation; a new conversation lists unclaimed handoff files, press 1 to resume.1
12. 60graceful-stopRctt27/graceful-stopWinds agents down cleanly as the session's credit runs out and has the orchestrator write a resume memo.1
13. 61handily-reply-viewniksavis/handilyLong replies fold to their first lines, tables draw with rules between their columns or in a full box with Table style box, each table and code block gets a copy button, and each prompt you type opens under a coloured rule labelled you.1
14. 62handoffAJclemendor/my-modsHand a task to a native context-sharing subtask with saved model and effort, one worktree, and a PR against main.1
15. 63handoffzaripovfarrukh/claude-code-modsHands a long session over to a fresh one before context runs out: watches the context fill, offers to write HANDOFF.md from the session's own transcript, and loads it into the next session.1
16. 64lumberroom-memorylumberroom/lumberroom-claude-codelumberroom as Claude Code's memory: the digest in the system prompt, a periodic search-and-write reminder, optional per-prompt recall, built-in memory off.1
17. 65model-hinthashswingingslasher/model-hintSuggests haiku, sonnet or opus for the task you are typing, live, in a band above the prompt. Instant word rules, then a small model reads the draft when you pause.1
18. 66neo4j-memorytroglodyte/claude-sqlite-memPersistent memory for Claude Code in a local SQLite file (node:sqlite; no server, no container). Injects standing facts and a subsystem map at session start, captures new facts at compaction and session end, and exposes search tools. A machine's Neo4j graph moves across by itself on first start.1
19. 67segmemmahuebel/segmemSegmented, scoped memory for agents: one file, SQLite, no daemon. Wake at session start, recall on every prompt, staleness nag at stop.1
20. 68session-handoffm-tababi/session-handoffWrites a structured session handoff on demand to ~/.claude/handoffs/<project>/ (never into the project), resumes from the newest one, restarts into a fresh conversation with the handoff (pill or /handoff fresh) and hints once when the context fills up.1
21. 69snagon-dev-modsphantanphatdgteam-gif/snagon-dev-modsA coding-agent harness for Claude Code as a mod that needs only Claude Code: /snagon-setup writes your project instructions without repeating the harness, a per-project memory (SQLite full-text search over JSONL, kept out of git), a fact-forcing safety gate with git hook-bypass and secret checks, session journal reminders, end-of-session handoff, cost and context notices, a flow that takes TypeScript and Python features from plan to release under the owner's approvals (tickets, tests first, a sandboxed judge, review, verify, ship), plus 64 skills, 66 agents and 43 commands.1
22. 70style-copMDmubarak786/claude-modsEnforce the style rules Claude keeps ignoring: banned words and phrases, a comment-density cap on added code, and files that must not gain comments. Rules live in .claude/style-cop.md and are both shown to Claude and enforced on edits.1
23. 71walkthroughenhki/claude-modsA 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 message1
24. 72handoff-packYeonwooSung/my-claude-code-modsHandoff Pack1.1k
25. 73auto-handoffpromptadvisers/claude-mods-starter-kitWrites a cold-start handoff to handoff/ before the context fills up or compacts, and offers to resume from it in the next session.21
26. 74thriftersinkoc/claude-modsKOZMOS Thrift: a frugal mode. /thrift on|off|auto; while on, every prompt carries a short note asking Claude to be economical (targeted reads, no broad searches or subagents unless needed, concise answers). Auto turns it on when the 5-hour or weekly limit passes autoAt and off after the window resets. A band with a spinning coin, and /thrift compares the average cost of thrift turns with normal ones.21
27. 7512uijust-every/12ui-claude-pluginA Design workspace in Claude Code: see design options for a UI as images, select one, ask for more, ask for a change with a note and hand an option off to be built. Your agent runs the 12ui command line once per request, which draws every option at once with your own Codex sign-in.
28. 76agent-cockpitdgsantana/claude-modsThe instruments around each Claude Code session: themed status line, TTSR and layered rules, AGENTS.md and APPEND_SYSTEM, an edit advisor
29. 77anchordarshk07/claude-modsAnchor: pin facts, decisions and rules that are re-sent every turn, so /compact can never lose them. Per-project pinboard with a panel.
30. 78arch-mapuseloadflow-dev/session-health-claude-code-modA side pane that draws the architecture of what you're building, version by version: what changed and why, a request traced through it, a design lesson, design-level security risks, and click-to-explain parts.
31. 79auto-handoffAmel-DZRV/claude-code-auto-handoffShows a context bar with a red handoff mark, the prompt-cache countdown and per-request tokens. When context passes a threshold it writes a handoff summary, clears the session and loads the summary into the fresh one. /keepwarm pings the prompt cache while you are away (pings spend tokens).
32. 80auto-handoffdhrubo55/claude-modsWrites a handoff by itself shortly before the prompt cache of an idle session expires, while the cache is still warm. Runs its own /auto-handoff:handoff skill and saves its answer under ~/.claude/handoffs, or another installed handoff command you pick once. Nothing in the handoff waits for approval: calls that would prompt are declined, never approved. A row above the prompt counts down; /auto-handoff opens a pane with the timeline, which command runs and why, and buttons to hand off now, pause, re-pick or copy the path.
33. 81auto-handoffm2ai-portfolio/claude-modsWrites a /next handoff automatically once a 1M-token session crosses 300k tokens and before every compaction, so the next session can /prime from it. Never blocks tool calls: goals and loops keep running (pair with autoCompactWindow: 300000). /auto-handoff on|off and threshold <n> are kept across sessions.
34. 82cassandraAraneaDev/cassandraRemembers the tool calls that already failed, and says so before your agent runs one again unchanged.
35. 83clean-codeptrzptrz888-create/claude-modsSetzt Clean-Code-Regeln als Hooks um: Lint-Hinweis nach Code-Änderungen, Referenzordner mit Quellcode der Bibliotheken und Schutz für CLAUDE.md, AGENTS.md und Skills.
36. 84code-modernizationBorgerod/claude-files-officeGuided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
37. 85code-modernizationmrkhachaturov/ccode-personal-pluginsGuided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
38. 86code-modernizationxotong/claude-marketplaceGuided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
39. 87cold-handoffSyntacticFlow/claude-mods/cold-handoff: Haiku summarizes the session and copies the summary plus the last 2 messages to the clipboard for a fresh session
40. 88collaborative-notesaprilxuMLC/claude-collaborative-notesA shared notes pane beside the conversation: capture, quote, and come back to what matters.
41. 89compact-handoffAnExiledDev/compact-handoff-pluginReplaces the engine's compaction with a subagent's handoff, and measures whether it can be one
42. 90compact-instructionsm-mizutani/dotfilesTell every compaction summary to keep user decisions, corrections, supplied material and the sources to re-read.
43. 91compact-keeperJvrd97/claude-compact-keeperCompaction without amnesia: the summarizer is told to keep your goal, constraints, decisions and paths verbatim, a card with your goal, prompts, pinned notes, edited files and open todos follows the summary, and the full transcript before compaction is archived as markdown.
44. 92context-handoffulttla/claude-mod-repoPast a context threshold, records a hand-off and continues the work from the notes: in a new desktop-app session by default, or in this one after a compaction or the app's clear
45. 93context-handoffVibe-Commit/claude-context-modsIn the 60-70% context band, Claude writes a handoff, the handoff is rewound away, the session compacts, and Claude resumes from the file.
46. 94coordinatorazoof-ahmed/claude-modsRun many worker agents from one coordinator session: scaffolded rules, lane cards and briefs, spawn/retire/respawn workers in orca, tmux, Windows Terminal or by hand, a scheduler worker for heavy jobs, a question queue, status reports, token-economy reminders, and a usage watcher with a graceful pause and resume.
47. 95council-of-elrondDeluha/council-of-elrondA council of specialist reviewers that gates risky tool calls before they run. Rules decide the tier; model members give a second opinion; anything uncertain comes to you.
48. 96difnotemmedum/difnoteReview the diff of what changed in the folders Claude works in since you last looked, write a note on any line or hunk, and get your notes in the prompt to edit and send back