Memory Bank text-based update workflow following integrated-rules v6.12. Use when updating memory bank files manually via markdown editing — creating edit chunks, updating tasks.md, session_cache.md, session files, and task files. NOT for database-native workflows (use mb-db-workflow instead). Triggers on phrases like "update memory bank", "create edit chunk", "update tasks.md", "update session cache", "memory bank update workflow".
Memory
mem-update
Try itMemory Bank Update Workflow — v6.12 compliant with project-repo awareness. Use when the user invokes $mem-update or asks for this workflow by name.
What it does
Memory Bank Update Workflow — v6.12 compliant with project-repo awareness. Use when the user invokes $mem-update or asks for this workflow by name.
The skill document
mem-update (Sage Adaptation)
This skill is adapted from a personal Codex skill. Key changes:
- Step 0 added: Project-repo awareness (check timesarrow/code repos before workspace)
- Paths updated: Point to
~/.openclaw/workspace/code/mb-core/instead of Windsurf paths - Approval relaxed: Location verification instead of explicit user approval
- Cross-repo checks: Prevents duplicate tasks across workspace and project repos
Memory Bank Update Workflow (Enhanced v6.12 Compliance — Sage Adapted)
Step 0: Identify Correct Memory Bank Location
- Check if working on a project: Before touching ANY memory-bank files, determine:
- Is there an active project with its own memory-bank? (e.g.,
timesarrow/memory-bank/) - Is this workspace/infrastructure work? (e.g.,
~/.openclaw/workspace/memory-bank/)
- Is there an active project with its own memory-bank? (e.g.,
- Rule: Project tasks → project memory-bank. Workspace tasks → workspace memory-bank.
- Scan locations:
~/.openclaw/workspace/code/*/memory-bank/(project repos)~/.openclaw/workspace/memory-bank/(workspace)~/.openclaw/workspace/code/mb-core/(mb-core repo for reference)
Step 1: Read Memory Bank Update Protocol
- First Action: Read the memory bank update protocol from
~/.openclaw/workspace/code/mb-core/integrated-rules-v6.12.md(Sections 1.5, 1.6, and 6.5) - Alternative: If mb-core doesn't have it, check
memory-bank/integrated-rules-v6.12.mdin the target repo - Purpose: Understand strict compliance requirements, file operation standards, and approval protocols
- Critical: Must read this before making any file modifications
Step 2: Deep Memory Bank Scan
- Comprehensive Scan: Perform deep scan of ENTIRE memory bank structure across ALL relevant repos
- Identify Related Content:
- All existing tasks in
memory-bank/tasks/related to current work (check ALL project repos) - All sub-tasks and implementation details in
memory-bank/implementation-details/ - Relevant session files and cache entries
- Current active context and task registry
- All existing tasks in
- Critical: If a task exists in a project repo (e.g., timesarrow), DO NOT create it in workspace memory-bank
- Analysis: Determine relationships and dependencies between existing documentation
Step 3: Verify Location Before Creating
- Assessment: Based on deep scan, determine if new tasks, sub-tasks, or implementation docs are needed
- Location Check: Before creating ANY new file, verify:
- Does this task already exist in another repo's memory-bank?
- Is this project work or workspace infrastructure work?
- What is the CORRECT memory-bank location?
- If unsure: Ask user for confirmation of correct location
- Prevention: Never create duplicate tasks across workspace and project repos
Step 4: Initialize Context (Time & Timezone)
- Get Current Time: Determine current system time and timezone (IST format:
YYYY-MM-DD HH:MM:SS TZ) - Verify Timestamp Standards: Ensure compliance with v6.12 timestamp requirements
- Prepare for Updates: Have accurate timestamps ready for all file updates
Step 5: Update Specific Files (Task/Implementation)
- Template Compliance: All file updates MUST follow the exact formats given in
~/.openclaw/workspace/code/mb-core/memory-bank/templates/folder - Available Templates:
task-template.mdfor new task filestasks.mdfor task registrysession_cache.mdfor session cacheedit_history.mdfor edit historyactiveContext.mdfor active context- And other specialized templates as needed
- Targeted Updates: Update only the specific task files and implementation docs identified in Steps 0-2
- Strict Rule: Use
edit_block(or equivalent) for updates. Never overwrite whole files unless creating new ones - Schema Compliance: Follow v6.12 requirements AND template formats exactly
- Cross-repo awareness: When updating, check if linked files exist in the same repo. Don't link to files in other repos unless intentional.
Step 6: Update Registries (Strict Schema Enforced)
tasks.md: Update status/timestamps- Constraint: Must match
| ID | Title | Status | Priority | Started | Dependencies | Details | - Constraint: Status must be
🔄,✅,⏸️, or❌ - Constraint: Details must be
[Details](tasks/Txx.md)
- Constraint: Must match
session_cache.md: Update active tasks/history
Step 7: Update Session Log
- Check for
sessions/YYYY-MM-DD-PERIOD.mdin the target repo - If exists: Update while PRESERVING EXISTING CONTENT. Append new work items
- If new: Create with standard header following v6.12 template
Step 8: Update History (Strict Regex Compliance)
edit_history.md: Prepend new entry- Header:
#### HH:MM:SS IST - TaskID: Description - Bullet:
- Actionrelative/path- Description - Action:
Created,Modified,Updated,Deleted
- Header:
Step 9: Finalize
- Generate Commit Message: Create commit message per v6.12 format
- Verify Compliance: Ensure all updates follow strict v6.12 requirements
- Document Completion: Note workflow completion in appropriate logs
Related skills
Global workflow for loading memory bank files based on recent activity and context Use when the user invokes $mem-load or asks for this workflow by name.
Memory Bank Template Compliance Cleaner Workflow Use when the user invokes $mem-format or asks for this workflow by name.
Global Memory Bank Deep Scan and Task Analysis Workflow — Multi-repo aware. Use when the user invokes $mem-scan or asks for this workflow by name.
Record and read Memory Bank state via mb-cli. Use for projects with memory-bank/database/ and a memory_bank.db. Triggers on: db workflow, record session work...
Initialize a memory bank for a new or existing project following the v6.12 protocol. Use when starting work on a project that lacks memory-bank documentation...