Handover
Prepare a handover for continuing work in a new session. Use when the user asks to "hand over", "prepare handover", "wrap up for a new session", or "context dump".
Install
$ agentstack add skill-gjoranv-claude-plan-skills-handover ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-gjoranv-claude-plan-skills-handover) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Prepare everything needed for a new conversation to continue the current work seamlessly.
- Gather state:
- Current repo and branch
- Uncommitted changes (
git status,git diff --stat) - Recent commits on this branch
- The plan issue (from argument, or ask the user)
- Summarize the session: What was done, key decisions made, what's still in progress, any blockers or open questions.
- Offer to persist state before handing over:
- Update the plan issue (
/gh-update-plan) - Commit uncommitted changes
Ask the user which of these to do. Skip any already done.
- Capture learnings: Review the conversation for surprises, gotchas, corrections, and non-obvious decisions. Propose where each belongs:
- Instructions file (CLAUDE.md, AGENTS.md, or similar): conventions, build quirks
- Repo docs: architecture insights, design rationale
- Agent memory: cross-project patterns, user preferences
User approves, edits, or drops each suggestion.
- Generate a handover prompt that the user can paste into a new session. Include:
- The plan issue reference (e.g.
/gh-read-plan owner/repo#12) - The repo and branch to work in
- A 3-5 sentence summary of where things left off
- The specific next step to work on
- Any gotchas or context the new session needs (e.g. "the tests pass locally but CI needs a config change first")
Rules:
- Keep the handover prompt concise. It should be copy-pasteable in one go.
- Do not include implementation details the plan issue already captures.
- If there's no plan issue, still generate a useful handover prompt with the repo, branch, and summary.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gjoranv
- Source: gjoranv/claude-plan-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.