490 context & memory Claude Code mods, most popular first. The most popular is ruflo-ai-team. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| ruflo-ai-team Give Claude a tenant-isolated AI team that divides work, coordinates progress, recalls approved context, and r | 76.1k ★ | Low risk |
| ruflo-daa Dynamic Agentic Architecture — 8 daa_* MCP tools for adaptive agents (create/adapt), cognitive patterns, workf | 76.1k ★ | Low risk |
| ruflo-ddd Domain-Driven Design scaffolding — bounded contexts, aggregate roots, domain events, value objects, repositori | 76.1k ★ | Low risk |
| fast-jev-compaction Verbatim Jev-guided compaction for Claude Code sessions. | 7.7k ★ | Review before installing |
| caliber-jev-compaction Verbatim Jev-guided compaction for Claude Code sessions. | 1.3k ★ | Review before installing |
| storybloq Project memory for Claude Code and Codex. Storybloq stores tickets, issues, handovers, and lessons in a .story | 773 ★ | Low risk |
| operator Durable project and user memory for agent-driven development in Claude Code. | 465 ★ | Review before installing |
| jev-auto-compact Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips | 442 ★ | Review before installing |
| memory-lens Recalls the few memories related to each prompt: one line for the human, one context entry for the model. Loca | 296 ★ | Review before installing |
| compact-adviser Suggests (or, opt-in, runs) /compact at a completed checkpoint, judged by TypeSafe Jev. Its hooks module activ | 218 ★ | High risk |
| winnow A calibrated context sieve for Claude Code. Every large tool result is judged by a System One model before it | 112 ★ | Review before installing |
| transcripted-live The meeting Transcripted is recording, inside Claude Code: Claude gets the call as context, a live dashboard ( | 80 ★ | Review before installing |
| tool-lines Draws each tool call as one compact 'tool_call: Tool(input) - meta' line and hides its result block | 80 ★ | Low risk |
| auto-handoff Hands a Claude Code session off to a fresh one before the context fills: a Haiku-written brief, /clear, and a | 77 ★ | High risk |
| desktop-context-map Chart context headroom and sampled window growth. | 76 ★ | Low risk |
| desktop-json-desk Validate pasted JSON with a searchable key summary and formatted preview. | 76 ★ | Low risk |
| desktop-session-brief Combine observed tool and turn counts with a manual handoff note. | 76 ★ | Low risk |
| handoff-notes Keep a dated list of progress and next steps, then copy it. | 76 ★ | Low risk |
| json-browser Summarize top-level JSON keys with types and a formatted preview. | 76 ★ | Low risk |
| dream-pass A dreaming pass over Claude's memory folder: merges duplicates, rewrites stale entries, removes dead ones and | 72 ★ | Review before installing |
| memory-fork After each turn Haiku decides whether memory needs a change; a tool-less fork of the session drafts it and the | 72 ★ | Review before installing |
| archcore Spec-driven development and context engineering for AI coding agents, backed by project context in Git. | 69 ★ | Review before installing |
| lcm Lossless context management — DAG-based summarization that preserves every message | 56 ★ | High risk |
| context-report Prints which instruction files the engine loaded (tier, path, @ imports, size) once per context load, and hint | 51 ★ | Low risk |
| superpowers-v Compound V for Superpowers: triple parallel pre-flight (code archaeology + domain-expert advisor + library/doc | 40 ★ | Review before installing |
| kindex-modern Repo-local Kindex memory and durable tasks for Claude function hooks (Claude Code mod, 2.1.287+) | 36 ★ | Review before installing |
| glowup A glow-up for Claude Code: a cockpit pane for changes, subagents and context, an activity band, and shareable | 33 ★ | High risk |
| claude-jev Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instea | 25 ★ | High risk |
| lemo-recap 会话小结：把本次会话汇总成三行摘要 · 点了才生成，对话越长用量越多 / Session recap: summarizes this session in three lines · runs only when yo | 24 ★ | Low risk |
| lemo-todo 笔记：在面板记下笔记 · 压缩后自动摘要（Haiku）默认关闭，在「安全」页开启 / Notes: keep notes in the panel · Auto summary after compaction (Hai | 24 ★ | Low risk |
| jev Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract | 22 ★ | Review before installing |
| probe3 Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injecti | 22 ★ | Review before installing |
| spike-compact Spike: does $.session.compact() work from a plugin, and what does the session.compact event carry? | 22 ★ | Low risk |
| spike-handoff Spike: safe-boundary handoff (bundle written at turn.complete from the runtime bus) and $.turn.abort semantics | 22 ★ | Review before installing |
| auto-handoff Writes a cold-start handoff to handoff/ before the context fills up or compacts, and offers to resume from it | 20 ★ | Low risk |
| plan Planning mode guidelines and context injection | 18 ★ | Low risk |
| ballast KOZMOS Ballast: a context coach. A toast when the context window passes warnAt, then a band with an anchor and | 13 ★ | Low risk |
| clawdling KOZMOS Clawdling: a pixel crab companion that lives above the prompt. It blinks and sways, scuttles while tool | 13 ★ | Low risk |
| compass KOZMOS Compass: the single most useful hint under the prompt. In order: the 5-hour limit near its end with its | 13 ★ | Low risk |
| heartline KOZMOS Heartline: a neon EKG of the session drawn above the prompt. Every tool call is a spike colored by its | 13 ★ | Low risk |
| skies KOZMOS Skies: the session's weather above the prompt. Tool failures, context and rate-limit pressure, stalls a | 13 ★ | Review before installing |
| spectra KOZMOS Spectra: the context X-ray. The context window broken down by category as a heat grid with a ranked leg | 13 ★ | Low risk |
| vitals KOZMOS Vitals: a btop-style machine monitor sidebar. CPU with a braille history graph, RAM bar and history, di | 13 ★ | Review before installing |
| handoff-runner bg 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 | 13 ★ | Review before installing |
| working-memory 把 context window 畫成一顆腦：工具呼叫點亮對應腦區，用量越滿越擁擠，compact 時睡眠整理 | 13 ★ | Low risk |
| pixel-pet An animated pixel-art companion above your prompt that reacts to your session and your typing, with a live con | 13 ★ | High risk |
| qa-guide Shows Claude's questions in a side pane with context, option details, an AI explanation and answer history; al | 12 ★ | Review before installing |
| jev-pilot TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to | 12 ★ | High risk |
| jev-blindspot-band A one-glance summary of jev-blindspot in the band above the prompt: the blind spot count, the deeper question, | 12 ★ | Review before installing |
| awcompact Compacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, lear | 11 ★ | Low risk |
| context-restore Hands a skill or command call the current text of its file when the file changed on disk after the session loa | 11 ★ | Review before installing |
| flaky-memory Remembers which tests failed on which code, and tells the model when a failing test has both passed and failed | 11 ★ | Low risk |
| gemini-compact Moves compaction from Claude to Gemini: in summary mode Gemini summarizes the conversation and the newest mess | 11 ★ | Low risk |
| memory-save Loads MEMORY.md into the session and saves project learnings to it after every turn through a tool-less fork i | 11 ★ | High risk |
| output-flood Measures how much context each Bash command spent and tells the model, past a size limit, which narrower comma | 11 ★ | Low risk |
| pin-note Keeps the notes you pin with /pin-note for the whole session and sends them to the model again, word for word, | 11 ★ | Low risk |
| prompt-offload Writes a prompt longer than the limit (2000 characters by default) to a temp file and sends the model its firs | 11 ★ | High risk |
| sage-memory Keeps project and global memories in SQLite through a shared local daemon, hands the model the entries that ma | 11 ★ | High risk |
| csr-lens Painel ao lado da conversa com visão geral, agentes (quem chamou quem, recados e rodadas), turnos, diffs como | 10 ★ | Review before installing |
| compact-keeper After a compaction, adds one message with exact facts from before it: your latest prompt in full, up to 4 earl | 10 ★ | Low risk |
| context-xray A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, me | 10 ★ | Low risk |
| tg-pane Telegram in a Claude Code pane: private chats with replies, categories (all chats and folders), model summarie | 9 ★ | Review before installing |
| context-lens A live /context: a pinned line under the prompt with the window fill and the growth per turn, and /context-len | 9 ★ | Low risk |
| changes Every file Claude created or edited this session, with +/- line counts from git and one-click 'why?', summary | 9 ★ | Low risk |
| context-keeper Live context-window panel: what fills it, checkpoints before you compact or clear, and nudges before you hit t | 9 ★ | Low risk |
| quickbar A one-line launcher above the prompt: live context %, and one-click buttons for every claude-mods panel you ha | 9 ★ | Low risk |
| ccf Claude Context First — a context-first, spec-driven, wave-parallel development workflow. Keeps CLAUDE.md/.clau | 9 ★ | Review before installing |
| recap-plus Keeps a recap-plus summary of the session above the prompt: what it is for and where it stands; /recap-plus ad | 9 ★ | Low risk |
| context-diet Trims huge tool outputs (logs, JSON, diffs, grep, file lists) before they reach Claude's context, and saves th | 8 ★ | Low risk |
| viber From idea to committed code: interview, reviewed plan, task-by-task build, project memory that grows with ever | 8 ★ | Low risk |
| plain-view A quiet transcript: tool rows step aside and the agent's plan shows as a card above the prompt, with the curre | 7 ★ | Review before installing |
| compact-keeper Saves each compaction's summary, with the files edited before it, to ~/.claude/handoffs so the context before | 6 ★ | Review before installing |
| pin-board Pins standing notes with /pin that Claude keeps following after /compact and /clear; shows them in one row abo | 6 ★ | Low risk |
| brand-theme Dresses Claude Code in your brand: a branded spinner, tool rows and question dialog, plus a band above the pro | 6 ★ | Low risk |
| agent-ctx Each agent loop's own context %, measured per request; a one-line CONTEXT_PCT_ALERT rides that agent's next to | 6 ★ | Low risk |
| hide-diffs Shows a one-line summary instead of the diff under Edit, Write, NotebookEdit and Bash calls (ctrl+q), and fold | 5 ★ | Low risk |
| opm An opinionated engineering workflow for Claude Code: brainstorm -> plan -> TDD execution with fresh-context su | 5 ★ | Review before installing |
| delamain Run a hub session that spawns and steers detached Claude Code and Codex agents: briefs, a shared journal, inbo | 5 ★ | Low risk |
| remcycle Garbage collection for Claude Code's memory: gives a session what the dream accepted, recalls from the archive | 5 ★ | Low risk |
| context-alarm Warns when the context window passes a threshold (80% by default) and suggests /save-context before compaction | 5 ★ | Low risk |
| findmutlu-sounds Sound packs for the moments that need you: a prompt sent, a permission prompt, a long job done, a subagent bac | 5 ★ | High risk |
| fork-lineage Remembers which session a fork came from (renames never break it), shows it above the prompt, and sends a fork | 5 ★ | Review before installing |
| workface Keeps a long-running agent's working notes through every compaction: briefs the summarizer, re-attaches the no | 5 ★ | High risk |
| dopa-mode DOPA MODE (DOPA is short for dopamine) for Claude Code: fireworks for everything you do and every milestone Cl | 4 ★ | Review before installing |
| proc-stats Status line, task-manager pane and report of Claude Code's memory, CPU and uptime, and those of the processes | 4 ★ | Review before installing |
| coordinator-handoff Auto-submits /coordinator-handoff when a dotfiles coordinator session's context reaches the configured limit, | 4 ★ | Review before installing |
| night-feast A vampire feeds on every tool call Claude finishes while the moon tracks how full the context window is. Betwe | 4 ★ | Review before installing |
| jev-effort Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent | 3 ★ | Review before installing |
| mejora-prompts /mejora y una frase: Claude te hace 3-5 preguntas, escribe un prompt con contexto (sin rol), lo puntúa y lo co | 3 ★ | Low risk |
| tide Band above the prompt that shows the context window as a tide: a fill bar, the trend per turn, a sparkline of | 3 ★ | Low risk |
| workflow-gates Draws the agentic-workflows engine's gates in the band above the prompt — rows a click puts in the prompt and | 3 ★ | High risk |
| workflow-gates-rows Draws the transcript rows of what the workflow-gates mod sends — an answer as the question it answered and the | 3 ★ | Review before installing |
| codecraft A Minecraft-inspired HUD for Claude Code: hearts for context, armor for safety nets, XP for verified work, and | 3 ★ | Review before installing |
| jev-gate Jev Gate in one plugin: the orchestration gate, the extractive compactor, the Jev effort and model router and | 3 ★ | High risk |
| jev-gate-compact Task-aware extractive compaction with bounded Jev dependency selection and the native recent tail; on by defau | 3 ★ | Review before installing |
| voice-notify Speaks Claude Code turn results aloud with VOICEVOX on Windows, macOS and Linux (CLI); long turns are summariz | 3 ★ | High risk |
| claudesama My unofficial fan mod that makes Claude Code cute. Claude-sama, a small kami of words, reads along above your | 3 ★ | Review before installing |
| project-memory A repo's memory/ folder, shared through git: a Haiku agent reads it and returns only what the task needs, anot | 3 ★ | Low risk |
| aim-widget Where a command lands outside this folder: the kube context, cloud profile, Terraform workspace or database it | 3 ★ | Review before installing |
| boss-widget A boss fight against the context window: its health drops as context fills, and compaction defeats it. | 3 ★ | Low risk |