skills.rest
tody-agent
tody-agentCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

cm-continuity

Read and update CONTINUITY.md to persist project context across sessions.

48|23|Updated Mar 17, 2026
Search Tags:#learning#memory#continuity#error-tracking#session-persistence#ai-workflow#decision-trace
One-click install
npx skills add https://github.com/tody-agent/codymaster --skill cm-continuity
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cm-continuity
Source: https://github.com/tody-agent/codymaster/tree/main/projects/cm-ux-master/_root
Command: npx skills add https://github.com/tody-agent/codymaster --skill cm-continuity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persisting contextual memory across sessions prevents repeating mistakes and loss of progress.

Core Features & Use Cases

  • Keeps a persistent CONTINUITY.md working memory to preserve context across sessions.
  • Reads CONTINUITY.md at the start of a session and updates Mistakes & Learnings, Next Actions, and Key Decisions at the end.
  • Supports a simple, auditable memory flow for multi-agent workflows and long-running projects, ensuring traceable decisions.

Quick Start

Initialize the working memory for the current project using cm continuity init and begin tracking progress across sessions.

Frequently Asked Questions about cm-continuity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I maintain context and persist memory across AI sessions?▼

To maintain context and persist memory across AI sessions, initialize a CONTINUITY.md working memory file that logs Mistakes & Learnings, Next Actions, and Key Decisions at the start and end of each session.

What is the best way to prevent repeating mistakes in long-running projects?▼

Preventing repeated mistakes in long-running projects requires session persistence that tracks errors and learnings. Using a standardized memory file updated at session end ensures past mistakes are traceable and avoidable.

How do I track decisions and progress in multi-agent collaborative workflows?▼

Tracking decisions in multi-agent collaborative workflows involves applying an auditable memory flow. Agents read a shared context file at startup and append traceable decisions and next actions at completion.

How do I start tracking project continuity with a persistent memory file?▼

To start tracking project continuity, run an initialization command to generate the standardized CONTINUITY.md template. This sets up the structured logging needed for consistent progress and decision tracing.

Can I use session persistence for collaborative agent workflows without external dependencies?▼

Yes, session persistence for collaborative agent workflows operates without external dependencies. It relies entirely on reading and updating a local CONTINUITY.md file to manage context and trace decisions.

What should be included in session persistence logs for AI workflows?▼

Session persistence logs for AI workflows should include Mistakes & Learnings, Next Actions, and Key Decisions. Following explicit guidelines for these log entries ensures consistent learnings and traceable decisions.

Related Skills

Explore More Software Engineering Skills→
letta-ailetta-ai
3.0k

initializing-memory

Initialize or reorganize agent memory blocks into a structured schema.

Official
Advanced
stark-ai-destark-ai-de
4

handoff

Generate handoff documents summarizing thread context, decisions, and next steps.

Official
Basic
ysgdepaulaysgdepaula

sync-state

Synchronize shared .agent state with local memory files.

Community
Intermediate
shekerkammashekerkamma

log-correction

Log analyst mistakes and fixes in structured YAML correction logs.

Community
Intermediate