agentleFS
cukascukas/remembrall/skills/handoff/SKILL.md

handoff

Skill6 starsChanged 8 months agoMITView on GitHub

Save a structured handoff document so another Claude instance (or this one after /clear) can resume the work. Use when context is getting long, switching tasks, 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

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a structured handoff document that any Claude instance can read to resume this work.

    line 8
  2. Distinctive:

    Test status (passing/failing)

    line 19
  3. Very specific:

    If there's an active task list, pass all pending tasks via --tasks

    line 78
  4. Distinctive:

    Do NOT include raw code dumps — reference files and line numbers instead

    line 79
  5. Very specific:

    Only include files YOU modified this session in --files — not the user's other work

    line 81

“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

Session Handoff

Create a structured handoff document that any Claude instance can read to resume this work.

Steps

  1. Gather state — Review the current conversation to understand:
    • What task was requested
    • What has been completed so far
    • What remains to be done
    • Key decisions made and why
    • Files created or modified (collect the full list)
    • Current blockers or open questions
    • Test status (passing/failing)
    • Approaches tried that failed (with error messages)
    • Any task list items (check /tasks)
    • Active skill/workflow — If a skill was active (e.g., /plan-guarded, /bugfix, /refactor), note which skill and which phase/step the session was in
  2. Write the handoff — Pipe a markdown document to handoff-create.sh. The script handles all path computation, git patches, YAML frontmatter, and team copies automatically. Always pass --session-id with $CLAUDE_SESSION_ID so the handoff can be found by auto-resume after /clear.

    REMEMBRALL_ROOT="${CLAUDE_PLUGIN_ROOT:-$(cat /tmp/remembrall-meta/plugin-root 2>/dev/null)}"
    cat << 'HANDOFF_CONTENT' | bash "${REMEMBRALL_ROOT}/scripts/handoff-create.sh" \
      --cwd "$(pwd)" \
      --session-id "$CLAUDE_SESSION_ID" \
      --status "in_progress" \
      --files "file1.ts,file2.ts,file3.ts" \
      --tasks "Remaining task 1" "Remaining task 2" "Remaining task 3"
    # Session Handoff
    
    **Task:** [One-line description of what was requested]
    **Active Skill:** [Skill name if one was active, e.g., `/plan-guarded` Phase 2 step 3, `/bugfix` step 4 — or "none"]
    
    ## Completed
    - [Bullet list of what's done, with file paths]
    
    ## Next Step — Do This First
    [The EXACT next action. Not a list of everything remaining — just the single next thing to do. Be specific: "Run the test suite for auth module" not "continue testing". Include the file path and line number if applicable.]
    
    ## Remaining (after next step)
    - [Numbered list of what still needs to happen, in priority order]
    
    ## Failed Approaches
    - [Approaches tried and ruled out. For each: what was attempted, the exact error message or why it failed, and why it won't work. This prevents the next session from repeating the same dead ends.]
    
    ## Do NOT Do
    - [Things the next session must NOT do — files to leave alone, features that are done and should not be re-analyzed, rabbit holes to avoid]
    
    ## Key Decisions
    - [Important choices made and why — so the next instance doesn't re-debate them]
    
    ## Files Modified
    - [List of files changed in this session, with brief note of what changed]
    
    ## Context
    [Any important context the next instance needs — error messages, gotchas discovered, user preferences expressed during the session]
    
    ## Open Questions
    - [Anything unresolved that needs user input]
    HANDOFF_CONTENT

    Replace the placeholder content with actual information from this session. Replace the --files and --tasks arguments with real values.

  3. Confirm and continue — Then:
    • Autopilot mode (REMEMBRALL autonomous flag is active, or AUTONOMOUS MODE was mentioned in a recent nudge): Do NOT enter plan mode. Do NOT ask the user anything. Just say "Handoff saved" in one line and keep working on the next task. The handoff is a safety net — compaction will happen naturally and the session-resume hook will auto-inject it. This is the autopilot loop: save → keep working → compaction → auto-resume → keep working.
    • Attended mode, context is low (triggered by REMEMBRALL_WARN or REMEMBRALL_URGENT): call EnterPlanMode immediately. The session-resume hook will auto-inject the handoff after context clears. Do NOT tell the user to type /clear or /replay.
    • Manual invocation (context is fine): just confirm with a brief summary and continue working.

Rules

  • Be concise but complete — the next instance has zero context
  • Include file paths, not vague descriptions
  • If there's an active task list, pass all pending tasks via --tasks
  • Do NOT include raw code dumps — reference files and line numbers instead
  • The handoff must be self-contained: another Claude reading only this file should be able to continue
  • Only include files YOU modified this session in --files — not the user's other work
  • Set --status to blocked if work is stuck, paused if intentionally stopping

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.