Skip to content
Back to skills

Smcp Handoff

ASecurity

Resume prior work from a saved subagent-mcp handoff when the user says "handoff-resume", "resume handoff", or "resume work"; call handoff-read, then confirm intent with exactly 4 structured questions before acting, and know the handoff-write/read/clear lifecycle.

  • 3 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added August 30, 2026
ai-agentsgogitapi

Works with

  • api
  • mcp

Security analysis

A100/100

Scanned August 30, 2026

npx -y skills add Heretyc/subagent-mcp --skill smcp-handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Smcp Handoff?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Smcp Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/heretyc-smcp-handoff/badge)](https://www.skillsdirectory.com/skills/heretyc-smcp-handoff)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: smcp-handoff
version: 1.0.0
description: Resume prior work from a saved subagent-mcp handoff when the user says "handoff-resume", "resume handoff", or "resume work"; call handoff-read, then confirm intent with exactly 4 structured questions before acting, and know the handoff-write/read/clear lifecycle.
author: Lexi Blackburn (https://github.com/Heretyc/)
created: 2026-07-11
updated: 2026-07-22
---

# Handoff Resume

When triggered, call the `handoff-read` MCP tool for the current cwd first, read the saved handoff, then confirm the user's intent with EXACTLY 4 structured questions before acting on it. Confirm: resume objective, current blocker, files/state to preserve, and next concrete action plus permission to proceed in this session. `handoff-write` saves a compact resume record once 20% context utilization unlocks it (a fixed threshold: it is early on purpose, so the goal context shaped at the 15% latch is captured while the session can still describe it, and it is unaffected by the `contextCoaching` setting). `handoff-read` retrieves the saved record for this cwd and binds reminder re-append behavior to this reading session. `handoff-clear` deletes the saved record and overflow file, if any, for this cwd.

## Coach the writer (handoff-write)

A handoff record MUST carry a DEFINABLE AND ACHIEVABLE goal. When shaping the `/goal` prompt, state (1) a concrete goal, (2) a measurable done-condition the successor can check, and (3) the next concrete action to take first. Never write a vague "continue working": the successor cannot tell when such work is finished.

## Coach the successor (handoff-read)

After the 4-question confirm, RUN UNTIL the handoff's stated goals are achieved (its done-condition is met). If mandatory `write_required` fires at H=80 first, write a fresh handoff and keep working in the same session. After automatic compaction, `session_handoff_required` requires `handoff-read` followed by exactly 4 structured confirmation questions before task work resumes. Do not stop early for review pauses unless the handoff explicitly asks for them.

## Swarm master goal prompt (re-entry after a swarm stage-5 handoff)

A swarm master goal prompt is a printed block embedded in the user's opening
message after a stage-5 swarm handoff. It contains the overall objective, a
list of absolute plan file paths (one per sub-orchestrator), and the explicit
instruction to call `swarm(5)`. When the opening goal contains this pattern:

1. Call `handoff-read` and run the 4-question confirm as normal.
2. After confirm, call `swarm(5)` -- this is the designated post-handoff
   re-entry; the server registers stage 5 as done and returns stage-6 coaching.
3. Follow the server's stage-6 coaching exactly. It will instruct you to launch
   one sub-orchestrator per plan file path using `launch_agent` with
   `sub-orchestrator: true`.
4. Do NOT read the plan files yourself. Each sub-orchestrator reads its own
   plan file; you handle the paths only.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.