By abix5
Integration with Hindsight memory bank for storing and retrieving development decisions across sessions
Initialize Hindsight memory bank for the current project
Pause auto-recall and auto-save features
Search for information in Hindsight memory bank
Get AI analysis based on project memory
Rescan project to update memory with new findings and refresh outdated entries
This skill should be used when the user asks to "store decision", "save to memory", "remember this", "recall past decisions", "what did we decide", "check memory", or mentions "hindsight", "memory bank", "retain", "recall", "reflect". Also use proactively when architectural decisions are made, technologies are chosen, bugs are solved, or tradeoffs are discussed.
This skill should be used when the user asks "what did we decide", "check memory", "recall", "do we have info about", "was there a decision", or proactively before making architectural recommendations, technology choices, or design decisions. Also activate when context seems missing, a question about past decisions is asked, or the prompt involves patterns, conventions, infrastructure, or known bugs.
This skill should be used when the user asks for analysis based on past decisions, "what patterns have worked", "should we adopt X given our history", "what aligns with our conventions", or needs recommendations grounded in accumulated project knowledge.
This skill should be used when the user asks to "save to memory", "remember this", "store decision", or proactively when an architectural decision is made, technology is chosen, bug is solved, tradeoff discussed, convention established, constraint discovered, negative decision made, or user repeats context. Trigger phrases: "Let's use...", "We decided...", "The reason is...", "Remember that...", "From now on...", "The solution was...", "We chose X over Y...", "X doesn't work because...", "We don't use X because..."
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Persistent memory for AI-assisted development. Store decisions, recall context, and get analysis grounded in your project's history — across sessions.
Hindsight gives Claude Code a long-term memory bank. It automatically:
All of this works autonomously — no manual commands needed for day-to-day use.
hindsight CLI:
curl -fsSL https://hindsight.vectorize.io/get-cli | bash
# Add marketplace
/plugin marketplace add abix5/memory-hindsight
# Install plugin
/plugin install hindsight
# Initialize memory bank for your project
/hindsight:init
# That's it — the plugin works autonomously from here
Once initialized, the plugin will automatically recall relevant context before answering architecture/design questions and save important decisions as they happen. You can also use commands manually:
# Save a decision
/hindsight:retain Chose PostgreSQL for ACID transactions in payment service
# Search memories
/hindsight:recall database architecture
# AI analysis grounded in project history
/hindsight:reflect Should we add caching layer?
# Check what's configured
/hindsight:status
| Command | Description |
|---|---|
/hindsight:init | Initialize memory bank for current project |
/hindsight:retain | Save information to memory bank |
/hindsight:recall | Search for information in memory bank |
/hindsight:reflect | Get AI analysis based on project memory |
/hindsight:rescan | Rescan project to update memory with new findings |
/hindsight:status | Show auto-workflow status and settings |
/hindsight:pause | Pause auto-recall and auto-save |
/hindsight:resume | Resume auto-recall and auto-save |
The plugin uses hooks to manage memory without manual intervention:
| Event | What happens |
|---|---|
| Session start | Loads bank configuration, checks connectivity |
| Each prompt | Evaluates if memory recall would help, searches automatically |
| Conversation compaction | Saves unsaved decisions/insights before context is trimmed |
| Session stop | Checks for unsaved important knowledge |
| Category | When to use |
|---|---|
architecture | System design, components, DB schema |
tech-stack | Technology/library choices with reasoning |
patterns | Code patterns, implementation approaches |
decisions | Key decisions with reasoning |
tradeoffs | Compromises, what was sacrificed for what |
bugs | Non-trivial bugs: root cause + solution |
lessons | Insights, gotchas, unexpected behaviors |
requirements | Business constraints, SLAs |
conventions | Standards, naming, team agreements |
See examples/ for Docker Compose configuration:
cd examples
cp .env.example .env
# Edit .env with your LLM API key
docker-compose up -d
MIT
npx claudepluginhub abix5/memory-hindsight --plugin hindsightFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Complete developer toolkit for Claude Code