agentleFS
ValeheadValehead/ccBar/skills/session-handoff/SKILL.md

session-handoff

Skill1 starsChanged 15 days agoMITView on GitHub

Session handoff. Writes a self-contained plan for the current work to ~/.claude/plans/ so a fresh session with no context can pick it up, then prints a one-line prompt to paste into that session. Triggered automatically by ccBar's Stop hook at a context threshold, or run manually any time.

148 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

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 126 edited versions we read keep these.

  • 4

    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:

    Use the conversation already in your context.

    line 27
  2. Very specific:

    Only if the context shows a compaction summary, use Grep on transcript_path for specific detail the summary hides.

    line 29
  3. Very specific:

    Write it to <plans_dir>/<descriptive-kebab-name>.md.

    line 33
  4. Distinctive:

    Never invent. If something is unknown, the plan says it's unknown.

    line 46
  5. Distinctive:

    Don't continue the prior task, don't commit, don't push.

    line 57
  6. Distinctive:

    Write in the user's style, following any writing rules in their CLAUDE.md files or memory.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 126 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

Hand the current work to a fresh session. Args (when triggered by ccBar): session_id, transcript_path, cwd, plans_dir, prompt_template (quoted). On a manual run with no args, use ~/.claude/plans and Read and execute this plan at: {path}.

1. Source

Use the conversation already in your context. Do NOT Read the transcript file: it is several MB at this size and would pull a large part of the session back into context.

Only if the context shows a compaction summary, use Grep on transcript_path for specific detail the summary hides. Never read it whole. git status and git log in cwd are fine for confirming repo state.

2. Write the plan

Write it to <plans_dir>/<descriptive-kebab-name>.md. The name describes the work, not the date or session id. If the file exists, append -2, -3, and so on.

The plan must stand alone for a session with zero context. Sections:

  • Goal: what the work is for, with the original ask in the user's words where it matters
  • Current state: what's done, what's changed but uncommitted or only staged, what's verified vs. untested
  • Decisions: what was decided and why, including options rejected so the next session doesn't relitigate them
  • Files and IDs: exact files, paths, branches, issue/PR numbers, IDs involved
  • Next steps: ordered, concrete enough to execute
  • Verify: exact commands
  • Gotchas: environment quirks and traps hit in this session
  • Open questions: anything waiting on the user

Never invent. If something is unknown, the plan says it's unknown.

3. Output in chat

  • One short line on what the plan covers
  • Then prompt_template with {path} replaced by the plan's absolute path, on its own line so it's easy to copy

Nothing after that line.

4. Stop

Don't continue the prior task, don't commit, don't push.

Write in the user's style, following any writing rules in their CLAUDE.md files or memory.

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.