agentleFS
rishbjain1rishbjain1/claude-stack/skills/handoff/SKILL.md

handoff

Skill0 starsChanged 4 months agoMITView on GitHub

Dump full session state to a persistent memory file in the active project so context can be cleared and any future Claude session restores instantly. Use when user says "handoff", "save context", "dump memory", "clear safely", "remember everything", or before /clear.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-mapping, setup-ts-deep-modules and 10 more.

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.
  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 93 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 87 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 51 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 54 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When invoked, write a comprehensive memory dump so future Claude sessions can resume w/o losing knowledge.

    line 8
  2. Distinctive:

    After major shipped milestone

    line 16
  3. Distinctive:

    Use markdown w/ numbered sections.

    line 36
  4. Distinctive:

    Do NOT include secret values (API keys, tokens, passwords).

    line 59
  5. Distinctive:

    Do NOT bloat — every line earns its place.

    line 60
  6. Distinctive:

    Do NOT speculate — only document what shipped or what's locked.

    line 61
  7. Very specific:

    Write SESSION_MEMORY.md w/ everything above

    line 70

“Common” is measured: kept by at least 6 in 10 of the 172 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

/handoff — Session State Persistence

When invoked, write a comprehensive memory dump so future Claude sessions can resume w/o losing knowledge.

When to use

  • User about to /clear and wants knowledge to persist
  • Context window getting heavy (>50% used)
  • End of long working session
  • Before switching projects
  • After major shipped milestone

What to capture (in this order)

  1. Identity — who user is, contacts, current location/situation
  2. Active project — repo path, stack, deployed URL, recent changes
  3. Roadmap / locked plan — phases, priority order, blockers
  4. Live state snapshots — any numbers or system state the next session must not re-derive
  5. Decisions still open — pending actions, choices waiting on user
  6. User patterns — communication style preferences, tools used, do/don't rules
  7. Resume protocol — exact files to read first when context restored

Where to write

Primary: <repo>/.claude/SESSION_MEMORY.md Secondary (if applicable): append a summary to your long-term notes store Tertiary: insert priority rows into Supabase action_queue (or equivalent task DB) so plan visible on phone/PWA

Output format

Use markdown w/ numbered sections. Heavy use of bold + tables for scannability. End w/ explicit "How to resume from clear context" checklist.

After writing

  1. List files written
  2. Tell user: "Context dumped. Clear safely. Next session reads <path> first."
  3. Suggest the 3-5 line bootstrap message user pastes to next Claude:
    Read .claude/SESSION_MEMORY.md before doing anything else.
    Then read ROADMAP.md.
    Then ask me what to work on.

Auto-trigger conditions

Suggest /handoff proactively when:

  • Conversation exceeds ~40 turns
  • User mentions "context", "clear", "remember", "save"
  • Major work session winding down
  • Multiple tools loaded but mostly stale

Constraints

  • Do NOT include secret values (API keys, tokens, passwords). Reference names only.
  • Do NOT bloat — every line earns its place. Future Claude reads this in one pass.
  • Do NOT speculate — only document what shipped or what's locked. Speculation = noise.
  • Mark caveman-mode active/inactive so future session knows tone preference.

Example invocation

User: "context is getting big, save it" You:

  1. Identify active project (recent file edits / cwd)
  2. Pull live state (curl prod endpoints, query DB for current snapshot)
  3. Write SESSION_MEMORY.md w/ everything above
  4. Confirm + provide bootstrap message

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.