structured-handoff
Skill2 starsChanged 4 days agoMITView on GitHub
Compact, reference-based summary to pass work to another agent or phase without dumping context. Prepares a compact handoff when a task passes between agents or phases — goal, work done, artifacts, checks, open issues, next step — referencing files instead of dumping contents. Use when delegating to an agent, passing work, or resuming work.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acceptance-criteriaSkill
- decision-recordSkill
- hub-managerSkill
- memorySkill
- orchestratorSkill
- quality-gateSkill
- report-pdfSkill
- self-critiqueSkill
- source-verificationSkill
- task-intakeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
When delegating a subtask to an agent or receiving its results.
- Distinctive: line 46
No secrets or personal credentials in handoffs.
- Distinctive: line 47
If the handoff exceeds roughly twenty lines, you are likely copying content rather than referencing paths.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Structured Handoff
Passes work to the next agent or phase with minimal overhead, avoiding conversation dumps.
When to use
- When delegating a subtask to an agent or receiving its results.
- At the end of a workflow phase or a session that will resume later.
When not to use
- Work completed entirely within the same session without handovers.
- To summarize context already accessible to the receiver.
Procedure
- State the objective of the assignment and the success criteria.
- List files and sources read (paths), without pasting contents.
- Summarize actions executed in a few concise lines.
- List artifacts produced with their file paths.
- Report checks executed and their outcomes (tests, quality gates).
- Separate verified facts from assumptions and open issues.
- Specify the proposed next step.
Expected output
Assignment: … — criteria: …
Read: <paths>
Done: …
Artifacts: <paths>
Checks: <test/gate> → outcome
Facts: … | Assumptions: … | Open: …
Next step: …Attention
- No secrets or personal credentials in handoffs.
- If the handoff exceeds roughly twenty lines, you are likely copying content rather than referencing paths.
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
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.