Memory and context

11,848 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

save-context

1417

pioneerjeff-labs/packwright

Skill Claude CodeCodex

Use this skill at milestone handoff, session close, or when the user asks Atlas to preserve state.

not rated 5 14d ago A 0 tokens original MIT

stale-brain

1418

stalebrainlabs/stalebrain

Skill Claude CodeCodex

Audit AI agent memory and instruction files: CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md, copilot-instructions.md and every other major agent's memory files (13 agents, 18+ file locations) against the live repository. Use when the user runs /stale-brain or asks to audit, verify, refresh, lint, or fix agent memory…

not rated 5 1mo ago A 185 tokens original MIT

decisions

1419

zimalabs/code-decisions

Plugin Claude Code

Bundles 1 skill, 5 hooks · 23 tokens together

Gives your codebase a memory for why. Captures decisions automatically, surfaces them when you edit affected files.

not rated 5 2mo ago A tokens not measured original MIT

distill

1420

gapmiss/claude-sessions

Skill Claude CodeCodex

Distills the current Claude Code session into a structured Obsidian note with queryable YAML frontmatter. Use when the user wants to capture, summarize, or archive a coding session — e.g. at the end of a session, when wrapping up work, when asked to save session notes, or when using the /distill command. Produces a…

not rated 5 3d ago A 89 tokens original MIT

carryover

1421

Cfvillarroel/carryover

Plugin Claude Code

Bundles 1 skill, 13 commands, 4 hooks · 184 tokens together

Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.

not rated 5 28d ago A tokens not measured original MIT

session-summary

1422

IvanKuzyshyn/dotfiles

Command Claude Code

Create session{slug}{timestamp}.md with a complete summary of our session. Include.

not rated 5 3mo ago A 0 tokens original Unlicense

intake

1423

nemock/company-brain

Skill Claude CodeCodex

Interactive Q&A capture of company knowledge into typed nodes in a company-brain vault. Sub-modes - vision (dictation-friendly six-phase flow), for-doc (document-driven interview that walks a target doc's sections), product, persona, competitor, competitor-ifu, competitor-clearance, competitor-snapshot, metric…

not rated 5 3mo ago A 120 tokens original MIT

smartcompact

1424

codeprakhar25/smartcompact

Plugin Claude Code

Bundles 1 command, 1 hook · 17 tokens together

Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.

not rated 5 2mo ago A tokens not measured original MIT

claude-brief

1425

tigerquoll/claude-brief

Plugin Claude Code

Bundles 1 command, 4 hooks · 14 tokens together

A live, auto-refreshing per-session summary brief docked beside your Claude Code terminal — to quickly get up to speed when switching between parallel sessions.

not rated 5 today A tokens not measured original BSD-3-Clause

session-manager

1426

Enakoneschniy/claude-dev-stack

Skill Claude Code

A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.

not rated 5 8d ago A 108 tokens original MIT

lean-context

1427

asarnaout/lean-context

Plugin Claude Code

Bundles 1 skill · 49 tokens together

Distills verbose project documentation into terse, agent-optimized context files.

not rated 5 6mo ago A tokens not measured original MIT

session-orchestrator

1428

rocketmandrey/claude-recall

Skill Claude Code

Session orchestrator on top of the recall index of all Claude Code sessions: finds a past session by task description, dives in (context, project, skill, artifacts) and acts in one of three modes — finish here, hand off the resume command, or open the session in a new terminal window. Use when user asks: "find the…

not rated 5 2mo ago B 196 tokens original MIT

using-mem

1429

4thel00z/memories

Skill Claude CodeCodex

Use when starting a coding session, making design decisions, fixing bugs, or when the user asks to remember or recall something — manages persistent memory via the mem CLI across project and global scopes.

not rated 5 2mo ago A 41 tokens

metacog

1430

houtini-ai/metacog

Plugin Claude Code

Bundles 2 hooks

Real-time metacognition for Claude Code. Six senses detect stuck loops, validation bias, repeated errors, and circular actions. Learns what works across sessions.

not rated 5 4mo ago A tokens not measured original Apache-2.0

mental-model

1432

automazeio/mental-model-skill

Skill Claude CodeCodex

Maintains a living mental model of the codebase. Read mental-model.md before making changes, update it when discovering new patterns or behaviors.

not rated 5 7mo ago A 31 tokens original Apache-2.0

asobi

1433

azusachino/harus-skills

Skill Claude CodeCodex

Use Asobi's persistent SQLite knowledge graph for session continuity, durable task dispatch, keyword recall, and reusable skills.

not rated 5 changed today A 26 tokens original MIT

workspace-mirror

1435

ahadkhan9/workspace-mirror-skill

Skill Claude CodeCodex

Sync and backup Antigravity IDE sessions, transcripts, SQLite database metadata, and brain artifacts locally into a structured workspace directory (.gemini-local/) with a rich interactive viewer.html page. Use this skill whenever the user mentions backups, workspace syncing, fswatch real-time mirroring, viewing…

not rated 5 2mo ago B 82 tokens original MIT

lroy-stack/ai-pod-store

Skill Claude Code

Comprehensive audit of the SKAPARA AI shopping assistant — conversation quality, RAG retrieval, session memory, usage metering, tool execution, streaming UX, cost optimization, and security. Use when asked to audit the AI assistant, chatbot, conversation system, RAG pipeline, AI usage limits, or chat UX.

not rated 5 3mo ago A 69 tokens

project-context

1437

perhapsspy/project-legibility

Skill Codex

Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.

not rated 5 changed 6d ago A 32 tokens original MIT

savecontext

1438

AlexanderBoger/SaveContext

MCP server Claude CodeCodexCursor +2

MCP server "savecontext" as configured in AlexanderBoger/SaveContext. Runs savecontext with python. Needs 1 environment variable to run.

not rated 5 1mo ago A tokens not measured original Apache-2.0

ai-note-searcher

1439

jarmentor/obsidian-notebook-mcp

MCP server Claude CodeCodexCursor +2

MCP server "ai-note-searcher" as configured in jarmentor/obsidian-notebook-mcp. Runs /Volumes/Development/ai-note-searcher-5000/mcp-server.js with node. Needs 4 environment variables to run.

not rated 5 9mo ago A tokens not measured

reliquery

1440

the-essential/reliquery

Plugin Claude Code

Bundles 6 skills, 1 MCP server · 967 tokens together

AI memory and context management system for worldbuilding, co-writing, and roleplaying. Turns raw content into structured vault relics, indexes them into semantic memory, and maps entity relationships so Claude remembers your world between sessions.

not rated 5 3mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: