How do I install the Init Memory skill?

Run npx skillmds@latest add martimramos/init-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Init Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Init Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Init Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Init Memory?

martimramos (@martimramos) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Init Memory by martimramos — Agent Skill

Name: Init Memory
Author: martimramos

Init Memory

Scaffold the per-repo session-memory structure (docs/NOW.md, docs/log/ daily journals, CLAUDE.md protocol section). Use when the user says "init memory", "onboard this project", or accepts the new-project memory offer. Also handles "no memory" opt-out.

martimramos 0f6f41b 3 files · 4.2 KB Updated Sep 17, 2026

File contents

init-memory: scaffold per-repo session memory

Scaffold the Cairn session-memory methodology in the current repo. The design principle is files are earned, not scaffolded: only Tier 0 is created here, and everything else appears on first genuine need.

If the user is ACCEPTING (default path)

Guard: if docs/NOW.md already exists, say the repo already has the structure and stop.
Ask exactly one question: "What is this project, in one sentence?" Use it to seed NOW.md. Do not ask anything else.
Create Tier 0:
- docs/NOW.md from templates/NOW.md (in this skill's directory), seeded with the user's answer and today's real date.
- docs/log/YYYY-MM-DD.md. Get the date from date +%F, never from memory. First content: ## Session HH:MM - goal: scaffold session memory (time from date +%H:%M).
Wire CLAUDE.md: append the full content of templates/protocol.md to the repo's CLAUDE.md. Create CLAUDE.md if missing. If it exists, append after existing content with a blank line. Skip entirely if it already contains ## Session Memory Protocol (never duplicate).
Do NOT create GOTCHAS.md, REFERENCE.md, or ARCHITECTURE.md. They are created on first genuine need, per the protocol. Do not mention them as "missing".
If .claude/.no-memory exists in the repo, delete it (the user changed their mind).
Report what was created and suggest committing the new files. Do not commit unless asked.

If the user is DECLINING ("no memory", "don't ask again")

Create an empty marker file .claude/.no-memory in the repo root (create the .claude/ dir if needed) and confirm: the memory offer will never appear again in this repo. They can run /init-memory later to opt back in.

---name: init-memorydescription: Scaffold the per-repo session-memory structure (docs/NOW.md, docs/log/ daily journals, CLAUDE.md protocol section). Use when the user says "init memory", "onboard this project", or accepts the new-project memory offer. Also handles "no memory" opt-out.---# init-memory: scaffold per-repo session memoryScaffold the Cairn session-memory methodology in the current repo. The design principle is **files are earned, not scaffolded**: only Tier 0 is created here, and everything else appears on first genuine need.## If the user is ACCEPTING (default path)1. **Guard:** if `docs/NOW.md` already exists, say the repo already has the structure and stop.2. **Ask exactly one question:** "What is this project, in one sentence?" Use it to seed NOW.md. Do not ask anything else.3. **Create Tier 0:** - `docs/NOW.md` from `templates/NOW.md` (in this skill's directory), seeded with the user's answer and today's real date. - `docs/log/YYYY-MM-DD.md`. Get the date from `date +%F`, never from memory. First content: `## Session HH:MM - goal: scaffold session memory` (time from `date +%H:%M`).4. **Wire CLAUDE.md:** append the full content of `templates/protocol.md` to the repo's `CLAUDE.md`. Create `CLAUDE.md` if missing. If it exists, append after existing content with a blank line. Skip entirely if it already contains `## Session Memory Protocol` (never duplicate).5. **Do NOT create** `GOTCHAS.md`, `REFERENCE.md`, or `ARCHITECTURE.md`. They are created on first genuine need, per the protocol. Do not mention them as "missing".6. If `.claude/.no-memory` exists in the repo, delete it (the user changed their mind).7. Report what was created and suggest committing the new files. Do not commit unless asked.## If the user is DECLINING ("no memory", "don't ask again")Create an empty marker file `.claude/.no-memory` in the repo root (create the `.claude/` dir if needed) and confirm: the memory offer will never appear again in this repo. They can run `/init-memory` later to opt back in.

Frequently asked questions