smcp-handoff

smcp-handoff is a skill for Claude Code from Heretyc/subagent-mcp. It costs 65 tokens per session (702 once invoked), scanned A, original, Apache-2.0.

A handoff management skill for saving and resuming work between coding-agent sessions.

In plain words
What is it for?
Use it when resuming saved work with commands such as “resume handoff,” or when creating and clearing a structured handoff record.
Why use it?
It gives the next session a defined objective, current blocker, files to preserve, and a concrete next action instead of an unclear request to continue.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the subagent-mcp plugin — 8 skills, 3 hooks, 1 MCP server shipped together

Good fit Use it when resuming saved work with commands such as “resume handoff,” or when creating and clearing a structured handoff record.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heretyc/subagent-mcp/smcp-handoff
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Heretyc/subagent-mcp --skill smcp-handoff
Clone the repo
git clone --depth 1 https://github.com/Heretyc/subagent-mcp

Made for: Claude Code.

Or install subagent-mcp, the plugin that ships this one along with the rest of its 8 skills, 3 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for smcp-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/heretyc/subagent-mcp/smcp-handoff.svg)](https://agentmods.dev/skills/heretyc/subagent-mcp/smcp-handoff)
Your own site
<a href="https://agentmods.dev/skills/heretyc/subagent-mcp/smcp-handoff"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/smcp-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 702 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00702
Opus 5 $0.00032 $0.00351
Sonnet 5 $0.00013 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 8d ago against content hash 5e905dc31949, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

smcp-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/smcp-handoff/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

Read the full file on GitHub · 37 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 37 lines · 65 tokens per session scan A 5e905dc31949

Subscribe to this mod's changes

smcp-handoff is a skill published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 702 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

customer-success-management

Runs the ongoing relationship with accounts after the sale — segmenting coverage against account value, building a health score that predicts rather than describes, running reviews customers find worth attending, forecasting renewals honestly, and finding expansion that follows usage instead of quota. Use this to…

cbrock84/headcount · 85 tokens

chief-information-officer

The CIO's remit — running the technology the company works on, service quality, IT spend, and the boundary with product engineering. Use this to set IT priorities, decide what IT owns versus engineering, structure IT spend or an IT roadmap, judge whether to build, buy or outsource, or work out why IT is seen as a cost…

cbrock84/headcount · 79 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens

chief-operating-officer

Owns execution: how work actually gets done across the organization, including process, program management, capacity, vendors, supply chain, and service delivery. Use this when execution is the problem rather than strategy, to design or fix a process, to resolve cross-functional handoff failures, to plan capacity, to…

cbrock84/headcount · 94 tokens

head-of-pmo

The EPMO lead's remit — what the PMO governs, what it must never become, and how it earns standing rather than compliance. Use this to stand up or reform a PMO, decide what it should and should not control, judge whether it is adding value or overhead, or work out why teams route around it.

cbrock84/headcount · 72 tokens

chief-product-officer

Owns what gets built and why: product strategy, roadmap, discovery, user experience, and the definition of success for each release. Use this to decide what to build next, to cut scope, to turn a business goal into a product bet, to judge whether a feature is worth its cost, or when engineering and go-to-market…

cbrock84/headcount · 96 tokens