hariharapanigrahy/layerkit / skills/layerkit-session-handoff
layerkit-session-handoff
VerifiedWrite a runbook to memory so the next agent can resume the integration loop safely.
layerkit-session-handoff
End-of-session (or mid-pipeline) handoff: durable runbook under memory so another agent continues without re-inventing context.
Protocol
- Gather state:
layerkit repo status
layerkit proposal list
layerkit map list
layerkit agent status
layerkit memory index
layerkit doctor
- Prefer the handoff CLI (template + pipeline status + memory write):
layerkit handoff write \
--vendor <vendor> \
--goal "<one-sentence outcome>" \
--done "research: map validated" \
--done "author: source helper updated" \
--next "layerkit-privacy-review: confirm consent rules" \
--next "layerkit agent mark-done --step privacy --evidence <path>" \
--next "run package verification and checker review" \
--blocked "need live credentials from owner" \
--out memory
Writes {projectDir}/memory/runbooks/handoff-<vendor|project>.md and refreshes memory INDEX.
- Or author manually with required sections:
# Handoff runbook — <vendor or project>
## Goal
## Done
- skills completed, proposal ids, validate status
## In progress
- current skill, open files, partial drafts
## Blocked
- exact residual human questions; who to ask
## Evidence index
- key source URLs + memory paths
## Next 3 actions
1. ...
2. ...
3. ...
## Forbidden
- do not invent; do not apply without checker; do not open deny-paths
## Quality
- last package verification result; coverage if any
## Outcome checkpoints
- what had to pass; proof artifact; fallback if it failed
## Unresolved errors
- exact red gates, failing assertions, or residual risks
Manual persist:
layerkit memory append --type runbooks --title "handoff <vendor>" --vendor <vendor> --body-file ./handoff.md
layerkit memory index
- Point the next agent at:
{projectDir}/memory/INDEX.md+ this runbook +layerkit-orchestrate-integration. Resume fromlayerkit agent next.
Forbidden
- Dumping secrets, tokens, or raw PII into the runbook
- Claiming steps done without proposal/map evidence
- Instructing the next agent to invent missing fields
Success criteria
- Runbook in
{projectDir}/memory/runbooks/handoff-*.md - INDEX.md lists the entry
- Required headings present (Goal, Done, In progress, Blocked, Evidence index, Next 3 actions, Forbidden, Quality)
- Next actions are ordered and skill-named
- Residual human questions are explicit
- Outcome checkpoints and unresolved errors are explicit
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |