agentleFS
QBall-IncQBall-Inc/the-bulwark/skills/session-handoff/SKILL.md

session-handoff

Skill8 starsChanged 5 months agoMITView on GitHub

Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.

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

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 9

    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 handoff documents that enable seamless context transfer between sessions.

    line 15
  2. Distinctive:

    Use LF (Unix) line endings only.

    line 21
  3. Distinctive:

    Use the Write tool directly (handles line endings correctly)

    line 22
  4. Distinctive:

    Never copy-paste from Windows clipboard

    line 23
  5. Very specific:

    If you see ^M characters, rewrite the file

    line 24
  6. Very specific:

    Use [x] for complete, [ ] for incomplete

    line 121
  7. Distinctive:

    Document decisions that affect future work.

    line 127
  8. Distinctive:

    Always include these sections.

    line 131
  9. Distinctive:

    Before finalizing the handoff, perform a two-part memory reflection:

    line 135
  10. Distinctive:

    Filter: Only flag items that (a) will persist beyond this session, (b) haven't already been saved to memory during the session, and (c) …

    line 144
  11. Distinctive:

    Present candidates to the user for approval before writing: Do not silently update memory.

    line 146

“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

Create handoff documents that enable seamless context transfer between sessions.

Critical Requirements

Line Endings

Use LF (Unix) line endings only. Never CRLF.

  • Use the Write tool directly (handles line endings correctly)
  • Never copy-paste from Windows clipboard
  • If you see ^M characters, rewrite the file

File Naming

Pattern: sessions/session_{N}_{YYYYMMDD}.md

  • {N}: Session number (integer, no leading zeros)
  • {YYYYMMDD}: Date without separators

Examples: session_5_20260104.md (correct), session_05_20260104.md (wrong)

Handoff Template

# Session {N} Handoff

```yaml
session: {N}
date: {YYYY-MM-DD}
phase: "P{X} - {Phase Name}"
task: "P{X}.{Y} - {Task Name}"
status: {completed | in_progress | blocked}
tokens_end: "~{X}K ({Y}%)"
```

---

## Session Summary

{2-3 sentences on outcomes, not process. What was achieved?}

## What Was Accomplished

- [x] {Completed item with file path}
- [x] {Completed item with file path}
- [ ] {Incomplete item - carried forward}

## Files Created/Modified

| File | Action | Lines | Purpose |
|------|--------|-------|---------|
| {path} | Created | ~{N} | {Brief description} |
| {path} | Modified | +{N}/-{M} | {What changed} |

## Verification Status

| Check | Status | Notes |
|-------|--------|-------|
| Typecheck | {Pass/Fail/Skipped} | |
| Lint | {Pass/Fail/Skipped} | |
| Tests | {Pass/Fail/Skipped} | {X/Y if applicable} |

## Technical Decisions

### {Decision Title}
- **Decision**: {What was decided}
- **Rationale**: {Why}
- **Impact**: {What it affects}

## What's Next

1. {Specific actionable step}
2. {Next step}

## Blockers / Issues

{List blockers or "None"}

## Learnings

{Patterns discovered or "None"}

Section Guidelines

YAML Header (Required)

The YAML header enables metrics collection. All fields required:

FieldFormatExample
sessionIntegersession: 5
dateYYYY-MM-DDdate: 2026-01-04
phaseQuoted stringphase: "P1 - Foundation"
taskQuoted stringtask: "P1.2 - Test Auditor"
statusEnumstatus: completed
tokens_endQuoted stringtokens_end: "~95K (48%)"

Session Summary

Focus on outcomes not process. What was delivered?

Good: "Completed session-handoff skill with CRLF handling. Ready for use." Bad: "I started by reading files, then thought about structure, then wrote..."

What Was Accomplished

  • Use [x] for complete, [ ] for incomplete
  • Include file paths
  • Be specific

Technical Decisions

Document decisions that affect future work. Include rationale so future sessions understand WHY. Skip if no significant decisions.

Blockers / Learnings

Always include these sections. Write "None" if empty - don't omit.

Memory Reflection (Mandatory)

Before finalizing the handoff, perform a two-part memory reflection:

Part 1: Session Learnings → Memory Candidates

Review the session for durable insights worth persisting to memory:

  • Feedback from the user (corrections, confirmations, preferences)
  • Technical decisions that affect future sessions (not just this task)
  • Project context that would be lost without memory (deadlines, stakeholder constraints)

Filter: Only flag items that (a) will persist beyond this session, (b) haven't already been saved to memory during the session, and (c) aren't derivable from code/git.

Present candidates to the user for approval before writing. Do not silently update memory.

Part 2: Supersession Check

Review existing memory entries against current project state:

  • Has any memory been invalidated by work done this session?
  • Are there memories that reference completed phases, old file paths, or reversed decisions?
  • Can any two memories be merged into one?

Present proposed removals/updates to the user for approval before modifying.

Quick Checklist

Before finalizing:

  • File named session_{N}_{YYYYMMDD}.md
  • YAML header complete and valid
  • All sections present (even if "None")
  • Next steps are specific and actionable
  • No CRLF line endings
  • Memory reflection Part 1: session learnings reviewed with user, saved if approved
  • Memory reflection Part 2: existing memory checked for superseded entries

Examples

For detailed examples of completed and in-progress handoffs, see references/examples.md.

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.