agentleFS
desertcachedesertcache/agent-os/skills/session-handoff/SKILL.md

session-handoff

Skill0 starsChanged 9 months agoMITView on GitHub

Create a session handoff note for context continuity. Use when the user says "session handoff", "pause work", "save context", or "/session-handoff".

139 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ascii-diagram, research-fleet 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.
  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • SethGammonSkill

    research-fleet

    Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.

    Also in 3 projects that use this

  • vicoa-aiSkill

    live-preview

    Start a local app in the current user project, expose it through a tunnel, and return preview details in structured Markdown. Use when the user asks for a preview URL, public URL, shareable localhost, mobile/web preview, or tunnel setup.

    Also in 4 projects that use this

  • botlearn-aiSkill

    doc-gen

    Also in 4 projects that use this

  • flyingobsidianSkill

    terminology

    Read a codebase, find terminology, create/update definitions into a markdown document.

    Also in 3 projects that use this

  • Dizzy-TenSkill

    bug-diagnosis

    Diagnose bugs and product issues without modifying code. Use when the user explicitly invokes $bug-diagnosis or asks for diagnosis, root-cause analysis, issue classification, or fix strategy for code bugs, failing tests, configuration/dependency problems, deployment issues, performance regressions, data anomalies, or frontend/user-experience problems described through screenshots, annotations, logs, errors, or natural-language reports. Prioritize analysis and recommendations only; do not edit files.

    Also in 3 projects that use this

  • +1 more from SethGammon

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 6

    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:

    When invoked, create a clean handoff note summarizing the current session's work for future continuity.

    line 10
  2. Distinctive:

    Before context gets too large

    line 16
  3. Distinctive:

    When switching to a different project

    line 17
  4. Very specific:

    Create file in the vault Sessions folder (path from agent-os.config.json):

    line 21
  5. Distinctive:

    Update related project README: if significant changes were made:

    line 75
  6. Distinctive:

    Don't assume future Claude will have any context from this session

    line 84
  7. Distinctive:

    Keep it concise -- under 30 lines of content.

    line 86
  8. Very specific:

    All paths come from agent-os.config.json -- never hardcode user-specific paths

    line 87

“Common” is measured: kept by at least 6 in 10 of the 117 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

When invoked, create a clean handoff note summarizing the current session's work for future continuity.

When to Use

  • Pausing work mid-task
  • Ending a session with incomplete work
  • Before context gets too large
  • When switching to a different project

Output Location

Create file in the vault Sessions folder (path from agent-os.config.json):

<vaultPath>/Sessions/YYYY-MM-DD-topic.md

Where topic is a short kebab-case description (e.g., auth-refactor-wip).

Handoff Note Template

---
date: YYYY-MM-DD
tags: [session, project-name]
project: {vault-folder-name}
---

# {Topic}

## What Was Done
- [Completed item 1]
- [Completed item 2]
- [Completed item 3]

## Current State
[Describe the state of the code/work -- what's built, what's running, what's broken]

## Next Steps
1. [Most important next action]
2. [Second priority]
3. [Third priority]

## Decisions (if any)
- **[Decision]:** [rationale]

## Blockers (if any)
- [What's blocking and what it's waiting on]

Critical: The project: frontmatter field MUST match the vault folder name exactly (e.g., Agent-OS, Job-Search). This feeds the session-start project index. Use "general" if the session doesn't map to a specific project.

Execution Steps

  1. Gather context from the current conversation:
    • What was the user's original request?
    • What files were modified?
    • What decisions were made?
    • What's still pending?
  2. Identify blockers -- anything preventing progress
  3. List next steps in priority order
  4. Write the note to the Sessions folder
  5. Update related project README if significant changes were made:
    • Update at <vaultPath>/<projectVaultFolder>/README.md
  6. Confirm the handoff note location to the user

Rules

  • Be specific about file paths and line numbers
  • Include enough context that a fresh session can pick up quickly
  • Don't assume future Claude will have any context from this session
  • Include any error messages or unexpected behaviors encountered
  • Keep it concise -- under 30 lines of content. Only add Decisions or Blockers if they have content
  • All paths come from agent-os.config.json -- never hardcode user-specific paths

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.