handoff
Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
Skill by jesse-merhi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jesse-merhi-handoff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/handoff
What's inside
- Skill name
handoff- Description
- Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
- License
- MIT
- Instructions
- 71 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: references/session-routing.md, references/tmux-placement.md, references/worktree-isolation.md, references/repair-pr-handoffs.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# Handoff A handoff always creates or prepares a full independent session. Never use a subagent, delegated in-chat worker, or background agent for any part of a handoff. ## Prepare context Write one compact handoff document in the operating system's temporary directory. Include the objective, current state, evidence, files and commands already touched, blockers, validation, durable Obsidian research links, suggested skills, and next concrete actions. Link existing artifacts rather than copying them. Redact secrets and unnecessary personal data. Classify the relationship: - `continuation`: the new session advances the same objective, feature, investigation, review, or implementation; - `aside`: the user introduced a separate objective during the conversation. Default to `continuation` when the handoff directly continues the current work. Do not classify work as an aside merely because it can run independently. ## Detect the working surface Run `scripts/detect-handoff-surface`. Read [session-routing.md](references/session-routing.md), then use the first verified route: 1. the user's explicit destination; 2. the current verified tmux pane; 3. the current verified app session; 4. a supported app already running; 5. a fresh full terminal or ACPX session. A tmux process elsewhere on the machine does not make the current session a tmux session. App and CLI detection uses current process ancestry and native session markers before global process discovery. ## Launch the full session - In tmux, read [tmux-placement.md](references/tmux-placement.md). A continuation opens a new pane in the current window. An aside opens a new window in the current tmux session. - In the Codex app, create a fresh task in the same project for a continuation. Use a projectless task or the matching different project for an aside. Use a Codex worktree for editing when the repository requires isolation. - In Claude, use a fresh named Claude session or a tmux-launched interactive Claude session. Do not use Claude background agents. - From another harness targeting Codex, prefer a verified Codex app task API when available. Otherwise use a fresh named ACPX or interactive Codex session and report that it is not an app task. Use a fork only when the new full session genuinely needs raw conversation history. A continuation does not automatically require a fork because the handoff document carries its working context. Read [worktree-isolation.md](references/worktree-isolation.md) before an edit, repair, commit, or PR handoff. Read [repair-pr-handoffs.md](references/repair-pr-handoffs.md) for repair and PR work. ## Completion Report the handoff document path, relationship, detected surface and evidence, session placement, isolation, and verified launch status. A queued worktree or requested launch is not a started session. If the selected app has no verified task-creation path, stop and report that exact limitation instead of silently substituting a subagent.
From jesse-merhi/skills, MIT.
More from jesse-merhi/skills
- 0.569score
just-do-it
jesse-merhi
Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
feedback-hardening
jesse-merhi
Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-claude
jesse-merhi
Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-codex
jesse-merhi
Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
cleanup
jesse-merhi
Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers…
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
finding-discipline
jesse-merhi
Confirm actionable review findings, deduplicate root causes, and exclude nits, vague risks, and style notes.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
atlassian-cloudid-jira
jesse-merhi
Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
grilling
jesse-merhi
Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
model-writing-guides
jesse-merhi
Select model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
design
jesse-merhi
Route UI design work among production visual design, interaction and motion implementation, read-only motion review, and explicit multi-variant prototyping.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
design-technical-diagrams
jesse-merhi
Create or refine architecture, lifecycle, sequence, trust-boundary, decision, threat-model, SVG, or HTML diagrams that explain system relationships.
SkillBFreshness: B★ 4Claude Code +9 - 0.559score
improve-codebase-architecture
jesse-merhi
Review architecture for module depth, interfaces, locality, dependencies, and testability.
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Sep 4, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jesse-merhi/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jesse-merhi
- 0.569score
just-do-it
jesse-merhi
Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-codex
jesse-merhi
Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-claude
jesse-merhi
Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
feedback-hardening
jesse-merhi
Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then…
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
cleanup
jesse-merhi
Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers…
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
grilling
jesse-merhi
Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
SkillBFreshness: B★ 4Claude Code +9
Cite this page
handoff skill. Agent Mart. https://agentmart.dev/skills/jesse-merhi-handoff (last updated 2026-10-24)