momhq/mom/mom-fold
Claude Code and agent skill by momhq/mom
- community
Checking that the SKILL.md file is still in the repository.
Fold this project's newly captured sessions into the MOM markdown vault. Use when the user wants to wrap up, finish, close the session, save decisions, update memory, or prepare the vault before clearing context.
Install
npx vskill@latest install momhq/mom/mom-foldSKILL.md
Invoking this skill is the user's request to wrap up. Proceed with the flow below immediately — do not ask the user to confirm they want to fold.
Folding reads the events captured since the last fold and synthesizes them into the project's markdown vault under .mom/vault/. It is the end-of-session step that turns raw captured turns into navigable memory.
Preflight
Check that mom is on PATH:
If it is missing, tell the user MOM is not installed and ask permission to install it:
If the user agrees, run that command. If the user declines, stop. Do not install MOM without explicit permission.
Confirm a project is bound — capture and fold only work for a bound directory:
If it is missing, the directory is unbound and nothing has been captured. Tell the user to bind first with /mom-project, then stop.
Run
Folding is incremental — it only processes events newer than the last watermark — and uses an LLM engine, so it can take a moment. When it finishes, run:
and report a one-line summary: the new watermark offset, files written, and last fold time.
Rules
- Do not pass an
--engineflag unless the user explicitly asked for a specific engine. - If
mom vault foldreports there is nothing new, say so — folding again is a safe no-op. - Never edit files under
.mom/vault/by hand from this skill; folding owns them. - CLI flag surface — never invent flags. Before using any flag on any
momsubcommand, run<subcommand> --helpand confirm the flag appears. If it is not listed, do not use it.
Postflight (version hint)
Any mom ... command may print a banner to stderr like:
If you see that line, finish the task first, then add one short line at the end of your reply suggesting the upgrade. Do not run the upgrade yourself.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/mom-fold/SKILL.md
Popularity
- Repository stars
- 56
- Repository forks
- 6
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/momhq/mom/mom-fold)