agentleFS
KogaCyberKogaCyber/jarvis-skills/skills/session-memory/SKILL.md

session-memory

Skill0 starsChanged 3 months agoMITView on GitHub

Save what happened this session and restore context at the start of the next one — the "second brain" that survives context resets. Use at session end ("save session", "wrap up") and session start ("where were we", "what's the status").

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use skill-creator.

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.
  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user says "save session" / "wrap up" — or when a long session is clearly winding down, offer it:

    line 31
  2. Distinctive:

    Update Next — overwrite, don't append.

    line 34
  3. Distinctive:

    Add unresolved problems to Open Bugs

    line 35
  4. Distinctive:

    When the user names a project or asks "where were we":

    line 40
  5. Distinctive:

    Never store secrets in memory files

    line 50

“Common” is measured: kept by at least 6 in 10 of the 11 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

Session Memory

An AI session forgets everything when it ends. Your JARVIS doesn't — because every session writes its ending down and reads it back at the start of the next one.

Storage

Plain markdown, one file per project: ~/.jarvis/memory/<project>.md

# project-name

## Next
The single most important next action. Future-you starts here.

## Sessions
### YYYY-MM-DD
- what was done (2-5 bullets, specifics: commits, files, decisions)
- what broke and how it was fixed

## Open Bugs
- bug — where it lives, what triggers it

Save (session end)

When the user says "save session" / "wrap up" — or when a long session is clearly winding down, offer it:

  1. Summarize the session in 2-5 bullets — commits made, features shipped, bugs fixed
  2. Update Next — overwrite, don't append; it's a pointer, not a log
  3. Add unresolved problems to Open Bugs
  4. Prepend the dated entry under Sessions (newest first)

Restore (session start)

When the user names a project or asks "where were we":

  1. Read ~/.jarvis/memory/<project>.md
  2. Report back in 3 lines: last session date + what was done, current Next, open bugs count
  3. Then just start on Next unless told otherwise

Rules

  • Facts, not vibes: "fixed N+1 in /api/orders (commit abc123)" beats "improved performance"
  • Convert relative dates to absolute — "tomorrow" is meaningless in two weeks
  • Never store secrets in memory files

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.