Claude Code Project Memory and Handoffs
Make new Claude Code sessions pick up where the last one stopped: lean CLAUDE.md, decisions log, handoff file, SessionStart hook.
Before & after
Same prompt, same agent — the only difference is the skill.
You could keep better notes about your work. You might document decisions and architecture in a README or wiki. You could also try keeping a project journal or summary of what you did each day. You'd probably benefit from writing things down as you go, rather than trying to remember later. You could also ask Claude to refresh on what was done before. Would it help to have a structured summary format?
CROSS-SESSION MEMORY SYSTEM AUTO-CAPTURE (End of each session) • Semantic summary of edits: "Added OAuth login flow to auth.ts, decided against third-party library" • Decisions logged: Why we chose Prisma over TypeORM (performance + type safety) • Bugs fixed: Stack trace + root cause + solution (searchable) • Open TODOs with context • Embedding stored in local SQLite + vector index RETRIEVAL ON REOPEN (Automatic) Three-layer fetch: 1. Index layer: Keywords from your prompt (instant) 2. Timeline layer: Recent sessions first (2-week window default) 3. Detail layer: Full decision log, code snippets on demand WHEN YOU REOPEN TWO WEEKS LATER "Reopen project-alpha" → System injects: "Last 3 sessions: Added user auth (2 days ago), fixed N+1 query bugs (4 days ago), decided Prisma was sufficient" → You start with context intact, zero re-explanation tax OUTPUT FORMAT Personal wiki per project, updated auto-hourly Timeline view: when decisions happened Searchable decision log: "why did we choose X?" COST: Local SQLite storage (~50KB per project); zero API calls (embeddings run local)
About this skill
Stop re-explaining your repo every session. A new session loads stable facts, current decisions, and a handoff from the last session, and nothing else.
What it does
- Trims CLAUDE.md to durable facts and exact build, test, and run commands
- Seeds a dated decisions log with status, sourced to the conversation or git history
- Writes an end-of-session handoff and a SessionStart hook that injects it with branch and recent commits
- Tests the setup from a cold session
What you get
A trimmed CLAUDE.md, decisions.md, handoff.md, a SessionStart hook config and script, and a cold-start test.
Best for
Solo builders and teams juggling several codebases in Claude Code who lose time to re-context after a break.
SKILL.md preview
---
name: cross-session-project-memory
description: Set up a Claude Code project so a new session picks up where the last one left off - a lean CLAUDE.md for stable facts, a decisions log, a handoff file written at the end of each session, and a SessionStart hook that injects the current state - without bloating context or letting stale notes contradict the code. Use when the user says "Claude forgets my project every session", "I'm tired of re-explaining the codebase", "pick up where we left off", "set up project memory", "write a handoff for next session", "what did we decide about auth?", or casually "how do I make Claude remember this repo?"
---
… (sign up to view the full skill)More ai & agents skills
View all AI & Agents skills →New Skill Scaffolder
Create a new Claude Code skill correctly: right mechanism, valid name and folder, a triggering description, and a smoke test.
Skill Library Lint and Overlap Report
Lint every skill in a repo at once: frontmatter, name-folder match, weak descriptions, overlapping triggers, broken refs, plus a CI script.
Self-Verifying Agent Loop: Plan, Check, Retry, Close
Turns a goal into a task plan with machine-run checks, executes with retry caps, escalates, and refuses to close until verified.
Skill Test Runner (Trigger and A/B)
Test a skill in fresh sessions: ready-to-run prompts, commands, and rubric for trigger recall, false triggers, and blind A/B.