session-memory

Solid

Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.

AI & Automation 1,160 stars 71 forks Updated today MIT

Install

View on GitHub

Quality Score: 94/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
77
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Session Memory ## Overview Persistent memory system that survives Claude Code's message compaction. Uses three markdown files in `.claude/cc10x/` as a permission-free database for continuity, consistency, and pattern compounding. ## Memory Surfaces 1. **activeContext.md** -- Current focus, decisions, learnings, next steps, blockers 2. **patterns.md** -- Project conventions, architecture decisions, common gotchas, reusable solutions 3. **progress.md** -- Task completion tracking with verification evidence ## Iron Law EVERY WORKFLOW MUST: 1. LOAD memory at START (and before key decisions) 2. UPDATE memory at END (and after learnings/decisions) ## Stable Edit Anchors Safe section headers for Edit operations: - activeContext: `## Recent Changes`, `## Learnings`, `## References` - patterns: `## Common Gotchas`, `## Project SKILL_HINTS` - progress: `## Completed`, `## Verification` ## Read-Edit-Verify Pattern 1. Read file 2. Verify anchor exists 3. Edit with exact `old_string` 4. Read back to confirm ## Tool Rules - Use `Write()` for NEW files (permission-free) - Use `Edit()` for EXISTING files (permission-free) - Never use `Write()` to overwrite existing files - Never compound commands (`mkdir && cat`) ## When to Use - At the start of every CC10X workflow (load) - At the end of every CC10X workflow (update) - Before making key decisions (check patterns) - After discovering learnings or gotchas (persist) ## Agents Used All CC10X agents use this skill. The cc10x-ro...

Details

Author
a5c-ai
Repository
a5c-ai/babysitter
Created
4 months ago
Last Updated
today
Language
JavaScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

memory-kit

Persistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.md. Prevents context loss on compaction or session restart. Use when starting a session, before compaction, syncing context across teammates, or pruning stale memory entries. Trigger with "save memory", "load memory", "memory audit", "memory share".

2,274 Updated today
jeremylongshore
AI & Automation Listed

memory

Persistent project memory across sessions. Load on start, save on stop, merge across sessions.

79 Updated 6 days ago
ilang-ai
AI & Automation Listed

memory_road

Persistent 11-layer memory architecture for Claude Code · drop-in for any agent / any project. Substrate (continuity-kernel.service) captures every event to SQLite FOREVER · always-on · LLM-free · indestructible. Comprehension layers (FURROW → SCRIBE → CHRONICLER → CARTOGRAPHER → MINER+SMITH → HUNTSMAN) extract structured meaning over time. Snow plow workers stack parallel from RIGHT-NOW backwards through history · always sharpening recent recall first. Blank-slate workers + batch-5 + strip-CLAUDE.md = 15-25x throughput vs naive single-fire. Forward sweeper keeps the now-edge clean automatically. HUNTSMAN surfaces every unfinished item. CARTOGRAPHER clusters episodes by theme. MINER+SMITH propose lockable doctrines. Forced memory injection on every user prompt via hook · the agent CANNOT forget to use memory. CANONICAL TURN-ON ORDER (every fresh install) · 1. FOUNDATION · substrate (L0) + chunking (L1) → records everything forever 2. FORWARD MEMORY · forward sweeper + WATCHER → now-edge stays summarized 3. BA

1 Updated today
RickyPOnline
Data & Documents Listed

persistent-memory

Persists context across conversations as plain markdown so every future session can enrich a topic-scoped memory (e.g. `parenting`, `relationship-anna`, `work-history`, `project-acme`). Four operations: `write` (extract candidates, resolve as ADD / UPDATE / DELETE / NOOP per Mem0), `read` (load a ≤ 200-line INDEX; fetch detail entries on demand per Claude Code's MEMORY.md pattern), `consolidate` (sleep-style merge + prune), `forget` (delete or redact with audit). Three storage tiers: home (`~/.agent-memory/<scope>/`, default), project-local (gitignored), project-shared (committed). Strict never-store list (passwords, API keys, JWTs, credit cards, SSNs, private keys); mandatory consent preview before write. Documents scaling from markdown → SQLite FTS → vector DB → managed memory (Mem0 / Letta / Zep). Triggers on "remember this", "save to memory", "recall memory", "load memory", "what do you remember about", "consolidate memory", "forget that", "/persistent-memory".

4 Updated 2 days ago
mthines
AI & Automation Listed

bettermemory

Verification-grade memory between sessions. Use bettermemory's MCP tools (memory_search, memory_show, memory_write, memory_verify, memory_record_use, etc.) instead of writing to files when the user asks you to "remember" something or references shared context from a past session. Default is to NOT call memory_search; only retrieve when the user references context you don't have ("my project", "the script we wrote") or a request is ambiguous in a way stored preferences could resolve. Every hit carries a staleness_verdict (calendar + path-drift + commit-drift); when it isn't "fresh", spot-check a claim before relying and call memory_verify to attest. Every use should record a claim_excerpt so retrievals stay auditable.

0 Updated today
0Mattias