Claude Code memory & instructions mods

Notes, rules, CLAUDE.md and AGENTS.md handling, handoffs and context carried between sessions. Most popular first.

290 mods · showing 1–48

Pane & dashboard modsContext & usage modsGuard & safety modsGit & GitHub modsNotification & sound modsSpinner, theme & fun modsWorkflow modsStatus linesHooksSlash commandsPlugins & marketplacesWorkflow kitsOutput stylesThemes & HUDsNotifications & soundsDesktop, web & mobile appsUsage & cost trackersSessions & historyModel routers & proxiesMulti-agent & worktreesEditor integrationsConfig & memory
  1. 1agents-mdanthropics/claude-codeAGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.154k
  2. 2code-modernizationanthropics/claude-plugins-officialGuided 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).46k
  3. 3storybloqStorybloq/storybloqProject memory for Claude Code and Codex. Storybloq stores tickets, issues, handovers, and lessons in a .story/ folder inside your repo.787
  4. 4ruflo-agentdbruvnet/rufloSubstrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embeddings (10 embeddings_* tools incl. RaBitQ 32x quantization), and WASM HNSW pattern router (3 ruvllm_hnsw_* tools). As a mod (ADR-445): opt-in safe recall into the prompt, a write guard that keeps secrets out of memory, /agentdb, and a status file the console shows80k
  5. 5memory-lensyonatangross/orchestkitRecalls the few memories related to each prompt you send (never on automated turns or file tool calls): one line for the human, one context entry for the model. Local files only, no network on the hot path.300
  6. 6operatoraerovato/operator-memoryDurable project and user memory for agent-driven development in Claude Code.487
  7. 7ctx-handoffcablate/ctx-handoff-modTurns what you teach Claude into project notes, catches its usual slips, keeps the cache warm while you're away, and picks long sessions back up125
  8. 8auto-handoffalexknowshtml/claude-auto-handoffHands a Claude Code session off to a fresh one before the context fills: a Haiku-written brief, /clear, and a seed that points the new session at the brief.114
  9. 9jev-rulesEliaAlberti/jev-rulesJev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.66
  10. 10oh-my-fableJunhan2/oh-my-fableAnthropic's prompting-guide rules for Claude Code, always on (Opus 5.5, Fable 5.1; Sonnet 5.5, Haiku 5.5, Opus 5 and Sonnet 5 too): install and forget: the working rules load at every session start and reach subagents, unattended sessions are detected automatically and get the early-stop rules, sessions at xhigh or max effort get the stop-after-checks rule, /fable turns a rough request into a guide-aligned prompt, /fable-status shows what is in effect, /fable-audit finds which guide sections your own rules are missing, /fable-setup moves the rules into a rules file (recommended once).57
  11. 11cs-updatehex/claude-sessionsRelease notes for a pending cs update, once per launch, with 1 to install it in place; /cs-update reopens the pane.52
  12. 12code-modernizationthevibeworks/claude-code-docsGuided 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).166
  13. 13kindex-modernwandercom/kindexRepo-local Kindex memory and durable tasks for Claude function hooks (Claude Code mod, 2.1.287+)49
  14. 14roof-modkagamiurayama/claude-code-roof-modReplace Claude Code's built-in reminders with your own words: silence four nags, rename 'the user' in template sentences, drop the CLAUDE.md preamble.30
  15. 15harness-scopeshimo4228/harness-scopeTurn global skills, rules, agents and tools on or off per repo with named profiles. Add a one-line .claude/harness-scope.json to a repo; /harness-scope shows what is off6
  16. 16handoff-runnerHangghost/learning-hacker-claude-modbg session 在 worktree 做完的分支，由你在面板按一顆按鈕快轉進 main：交接單只帶參數，步驟由 mod 推導，執行前檢查、執行後驗證14
  17. 17scribenekyialabs/claude-code-toolkitA scribe for your memory tools: a small classifier reads each exchange and notices which memory tools it called for. Shadow mode logs; whisper mode nudges. It never writes to memory itself.14
  18. 18ruflo-rag-memoryruvnet/rufloRuVector memory with HNSW search, AgentDB, and semantic retrieval. As a mod (ADR-445): a write guard that keeps secrets out of memory, /rag-mod, and a status file the console shows80k
  19. 19agent-treeMikeGT4/agent-treeTerminal side pane that shows a session's agents as a live tree: stop a sub-agent, send it new instructions mid-task, switch its model and effort, change the look.13
  20. 20handoff-compacttrytofly94/handoff-compactReplaces Claude Code's compaction with a structured handoff: a fork of the session writes it from the prompt cache, and the conversation continues from exactly that handoff.12
  21. 21prompt-polishVedantAndhale/claude-pro-kitAn Improve button above the prompt (and /polish) rewrites your draft with Opus at low effort (/polish model picks another) using the prompt-master rules (MIT, nidhinjs/prompt-master); Undo puts the original back. Each press is one model call; its exact tokens are shown.12
  22. 22pin-memoYeonwooSung/my-claude-code-modsPersistent pinned memos and clickable todo checkboxes above the Claude Code prompt1.1k
  23. 23commonplacenoopz/commonplaceA knowledge vault Claude reads and keeps for any folder of notes: graph-indexed vault tools, private domains that stay sealed, connections to what you already wrote surfaced under answers, and [[note]] links in replies that are checked against the vault.11
  24. 24lesson-cardsyonatangross/orchestkitDisplays lesson hint cards when tool calls match known patterns. Advisory only: a lesson never blocks a tool call.300
  25. 25viberp2p2sp/p2p2.claudeFrom idea to committed code: interview, reviewed plan, task-by-task build, project memory that grows with every build.8
  26. 26workfacescodge-24/workfaceKeeps a long-running agent's working notes through every compaction: briefs the summarizer, re-attaches the notes after the summary, and shows them in a panel you can steer.7
  27. 27memory-forkray-amjad/claude-code-modsAfter each turn Haiku decides whether memory needs a change; a tool-less fork of the session drafts it and the mod writes it, with a band and a pane showing what changed101
  28. 28coordinator-handoffray-manaloto/dotfilesAuto-submits /coordinator-handoff when a dotfiles coordinator session's context reaches the configured limit, with a visible status-line heartbeat5
  29. 29delamainilya-kozyrev/delamainRun a hub session that spawns and steers detached Claude Code and Codex agents: briefs, a shared journal, inboxes, an owner-question register, a lock board, handoffs, and the agent-top console.5
  30. 30remcyclelianmatsuo/remcycleGarbage collection for Claude Code's memory: gives a session what the dream accepted, recalls from the archive, and shows what waits for your ruling.5
  31. 31proc-statsDragosMocrii/proc-statsStatus line, task-manager pane and report of Claude Code's memory, CPU and uptime, and those of the processes it started4
  32. 32sidekickFynnXland/fynn-modsChecks your message before it is sent, by rules and, where worthwhile, briefly with Haiku 5.5 (Sonnet 5.5 writes rewritten versions in level auto): a hint line under your message or a question (new chat with handoff, a skill, a clearer version, or "wrong chat?" when the message belongs to another project). Names due maintenance once per chat (/skill-doctor, prompt-audit, consolidate-memory, /init). With worklist installed, a long message with several tasks can be split into 3-4 to-dos, and /later plans text as to-dos. Five levels (off, cache, guide, plan, auto) with a colored label in the prompt footer. /savings shows cost and measurable savings at a glance, /savings detail compares the models over time. Optional, off by default (/sidekick notes on): while Claude works, a "good to know" note above the prompt when you likely missed something with consequences (one question to your main model over the conversation, every 6 steps). /sidekick help shows all commands and settings as a table.4
  33. 33cc-strategic-compactionsergiopalacio/cc-strategic-compactionCompacts the conversation when the rules say the moment is right, judged against the conversation itself at the end of a turn.3
  34. 34claudetto-you-should-knowxsyetopz/dotclaudeShows one short note above the prompt when a side check finds something about the work that the person very likely does not understand. It ships off. Once on, it makes one small bounded request every sixth step, sends nothing else out, and keeps no telemetry.3
  35. 35project-memorynoash-xrc/claude-toolsA repo's memory/ folder, shared through git: notes grouped in hubs, file-tied notes that load on touch, a pre-commit check, and a Haiku agent that keeps it in order3
  36. 36sc-workspacesimplecore-inc/claude-modsA workspace pane for Claude Code: agents and worktrees, checkpoints, notes, changes and memory files in one tabbed pane3
  37. 37ui-variantsDemeoStep/ui-variantsA live macOS picker window for Flutter UI variants: Claude writes the variants into a temporary app, and your choice, notes and revisions come back to the session3
  38. 38workflow-gates-rowsleeovery/portalDraws the transcript rows of what the workflow-gates mod sends — an answer as the question it answered and the answer, a handoff's continuation as where the work went — and a compaction's note as one dim line, instead of Claude Code's framing.3
  39. 39dream-passray-amjad/claude-code-modsA dreaming pass over Claude's memory folder: merges duplicates, rewrites stale entries, removes dead ones and tidies MEMORY.md, with a backup and undo101
  40. 4012ui-designjust-every/12ui-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.2
  41. 41apk-fraicheurDarkSawOktay/claude-modsAndroid APK freshness: is the APK up to date with the code, build in progress and its duration, failures and out-of-memory caught at once, size, copy to another folder. For React Native / Expo / Gradle projects. French or English.2
  42. 42auto-polishmako-code/gobworksEvery prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the goal in one line, the likely scope, the project's checks to keep green, and what done means. Haiku only for vague prompts; See, Undo and Off in the band.2
  43. 43code-kitwarrendeanlangeveldt/code-kitKeeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, protected paths with an approval log, spec-check and design gates, proof-before-finish checks, dispatch, review, build status and CI verification, configured per project from its docs2
  44. 44context-handoffAnkitrai97/rai-claude-modsA bar above the prompt showing how full the chat's context is (green under 60%, amber 60-80%, red above 80%), with an H button and /handoff to save a handoff note that the next chat in the project loads automatically.2
  45. 45dndrobinalexandre/claude-code-kitDo not disturb for the kit's panes: profiles that hide the history, the dev activity, the reminders or the handoffs, or keep only some repos and groups; turned on by hand, by Wi-Fi, by days and hours, or by folder. Its pane opens from the Configuration pane.2
  46. 46headspaceXabilimon1/emcc-claude-code-modsWhat Claude carries, in colour: a bar above the prompt with system, rules, conversation and large tool results, and a pane to turn rules off for the session, edit and save them, and take out large results.2
  47. 47MacLoadHeuwzen/claude-runwayShows your Mac's CPU and memory under the prompt, names the app behind a slowdown, and warns when the Mac is overloaded2
  48. 48recalljoeldg/claude-modsMakes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standing orders and second-opinion reviews into a local SQLite index (kept after Claude Code deletes old transcripts), gives Claude search, expand, recap and list tools, and adds /recall (search, last session, timeline, decisions, commands, files, PRs, ask), /remember, a pick-up-where-you-left-off band, a related-work band, and a per-session ledger (goal, open tasks, questions answered, files touched, PRs and commits) that comes back after a compaction and /recall ledger prints. Nothing calls a model except /recall ask: one call to the ask model per question, billed to your usage.2

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs →