agentleFS
Sign inStart free
faizkhairifaizkhairi/claude-code-blueprint/skills/save-session/SKILL.md

save-session

Skill73 starsChanged 4 months agoMITView on GitHub

MUST use when user says 'save', 'save session', or explicitly wants to preserve session state. {USER_NAME} does NOT use slash commands; also trigger proactively when significant work has been completed and session context should be persisted. For session endings (bye/done/goodbye), use the session-end skill instead which combines save-session + save-diary.

  • Commits and pushes

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ship.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prerequisite check (run first): if ./memory/ does not exist OR ~/.claude/.memory-disabled marker file is present, this skill is a no-op.

    line 7
  2. Distinctive:

    Ask the user if there are any pending tasks, deadlines, or reminders to carry forward

    line 18
  3. Distinctive:

    Remove completed reminders (move to Completed section with date), keep active ones, add new ones

    line 19
  4. Very specific:

    Update per-project context: If working on a registered project, update ./memory/projects/active/{project}.md → Session Context section:

    line 21
  5. Very specific:

    Check preferences.md: If new preferences or work patterns were observed during this session, update ./memory/core/preferences.md

    line 26
  6. Very specific:

    Check MEMORY.md: If new technical learnings or gotchas were discovered, update {MEMORY_MD_PATH}.

    line 28
  7. Very specific:

    Check decisions.md: If a non-obvious architectural or technical decision was made this session (something future-us would ask "why?"), …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prerequisite check (run first): if ./memory/ does not exist OR ~/.claude/.memory-disabled marker file is present, this skill is a no-op. Output: "Memory persistence is disabled. Run ./setup.sh and choose to enable memory if you want this skill to work."

Save session state to memory:

  1. Update session.md at ./memory/core/session.md:
    • Current topic and what we're working on
    • Recent progress (what was accomplished this session)
    • Next steps (what should happen next session)
    • Any blockers or open questions
  2. Update reminders at ./memory/core/reminders.md:
    • Ask the user if there are any pending tasks, deadlines, or reminders to carry forward
    • Remove completed reminders (move to Completed section with date), keep active ones, add new ones
  3. Update per-project context: If working on a registered project, update ./memory/projects/active/{project}.md → Session Context section:
    • Last worked on (what specifically)
    • In progress (current state)
    • Next up (what should happen next on THIS project)
  4. Check preferences.md: If new preferences or work patterns were observed during this session, update ./memory/core/preferences.md
  5. Check MEMORY.md: If new technical learnings or gotchas were discovered, update {MEMORY_MD_PATH}. After any edit, count total lines; if over 170, warn that MEMORY.md is approaching the 200-line auto-truncation limit and suggest moving content to topic files.
  6. Check decisions.md: If a non-obvious architectural or technical decision was made this session (something future-us would ask "why?"), append to ./memory/core/decisions.md using the existing format: ## YYYY-MM-DD: Title / **Context** / **Decision** / **Rationale**
  7. Diary (if this was a significant session, e.g., feature shipped, major bug fixed, architecture decision made): Use the save-diary skill to create or append an entry to ./memory/diary/current/YYYY-MM-DD.md
  8. Git commit + push memory: Stage all changed files in memory, commit with a descriptive message, and push to GitHub (git push origin main). This keeps the remote diary and session state up to date.
  9. Confirm: Summarize what was saved and where

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free