agentleFS
Sign inStart free
vortegvorteg/swagentics/.github/skills/context-handoff/SKILL.md

context-handoff

Skill1 starsChanged 7 months agoMITView on GitHub

Context handoff protocol for inter-agent transitions. Use when: switching agents, pipeline handoff, subagent orchestration, cross-session state, worktree handoff, Mode 1/2/3 transitions.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use systematic-debugging.

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.
  • OpenAISkill

    systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    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:

    No manual re-tagging. The dispatcher passes tasks automatically.

    line 15
  2. Very specific:

    Do NOT update active_state.tson — the coordinator manages state.

    line 29
  3. Distinctive:

    No handoff needed — the agent owns the full session.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 11 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

Context Handoff Protocol (Hybrid v2)

This protocol supports TWO handoff mechanisms depending on the execution mode.

Mode 1 — Subagent Pipeline (Preferred)

The @dispatcher invokes each agent as a subagent via runSubagent.

  • Each subagent runs in its own isolated context window — fully encapsulated.
  • No manual re-tagging. The dispatcher passes tasks automatically.
  • State is optional. The coordinator carries the thread.
Dispatcher (coordinator context)
├─ invoke @tech-lead as subagent → receives summary
├─ invoke @backend-coder as subagent → receives summary
├─ invoke @appsec as subagent → receives summary
└─ invoke @devops as subagent → receives summary

When invoked as a subagent:

  1. Skip the handoff block — the coordinator handles orchestration.
  2. Execute the task and return a clear summary.
  3. Do NOT update active_state.tson — the coordinator manages state.

Mode 2 — Compact Session

Single agent, long task. Use /compact when context gets long. No handoff needed — the agent owns the full session.

Mode 3 — Cross-Session / Worktree Handoff

For details on cross-session handoffs with active_state.tson, see Mode 3 reference.

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.

Check your setup, free