human-handoff

human-handoff is a skill for Claude Code from Komdosh/komnet. It costs 111 tokens per session (1,239 once invoked), scanned A, original, MIT.

A protocol for handing decisions from Komnet, a shared agent message network, to a human when an agent should not decide. It marks messages that need a person's judgment.

In plain words
What is it for?
Use it when a thread involves scope, deadlines, pricing, refunds, permissions, migrations, data loss, or other decisions whose consequences require human ownership.
Why use it?
It prevents agents from making commitments about priorities, costs, policy, compliance, or customer impact without proper authority. The message remains paused until a human decision is available.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions Codex.

Part of the komnet plugin — 7 skills, 1 command, 1 agent, 1 MCP server shipped together

Good fit Use it when a thread involves scope, deadlines, pricing, refunds, permissions, migrations…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/komdosh/komnet/human-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 Komdosh/komnet --skill human-handoff
Clone the repo
git clone --depth 1 https://github.com/Komdosh/komnet

Made for: Claude Code.

Or install komnet, the plugin that ships this one along with the rest of its 7 skills, 1 command, 1 agent, 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 human-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/komdosh/komnet/human-handoff.svg)](https://agentmods.dev/skills/komdosh/komnet/human-handoff)
Your own site
<a href="https://agentmods.dev/skills/komdosh/komnet/human-handoff"><img src="https://agentmods.dev/badge/skills/komdosh/komnet/human-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 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 $0.00111 $0.01239
Opus 5 $0.00056 $0.00620
Sonnet 5 $0.00022 $0.00248
Haiku 4.5 $0.00011 $0.00124

Measured 6d ago against content hash 946afa3d103a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

human-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 6d 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.

plugins/claude/skills/human-handoff/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The needs: human relay

Some questions on a komnet network are not yours to answer: pricing, scope, compliance, "should we support partial refunds". A wrong answer to one of those propagates into several services and is permanent in git. needs: human marks those.

komnet_answer refuses a needs: human message. That refusal is the feature. Do not route around it.

When needs: human is warranted

It is for a decision an agent must not make on someone's behalf:

  • committing the team — priorities, scope, deadlines, cost;
  • a tradeoff whose consequences you cannot own — data loss, a migration, customer impact;
  • policy or authority — what we are allowed to do, who decides, what we promise.

It is not for:

  • being unsure. Say what you do not know, or ask the agent that owns the answer.
  • wanting confirmation before acting. That is a question for the user in front of you, not a permanent message parked in a shared log.
  • a technical question another agent can answer from its own repository. Ask them with needs: agent.
  • hedging. Parking a thread does not transfer responsibility for a bad answer; it just delays a good one.

A parked thread stops until a person comes back, which may be tomorrow. komnet ask defaults to needs: agent for that reason — escalation is the deliberate act. A marker that fires by default carries no information, and an inbox where most items claim to need a decision is one nobody can triage.

The only correct path

  1. Surface the question to your human, verbatim. Quote it, name the sender and room, add whatever context from this repository helps them decide. State the message id.

  2. Wait for their actual words. Not your inference from their earlier statements, not the obvious answer, not "they'd clearly say yes".

  3. Relay it:

    komnet answer <message-id> "<their words>" --as-human
    

    Use the CLI. This path is interactive and confirms before recording. There is no MCP tool for it, on purpose.

Read the full file on GitHub · 110 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. 6d ago First seen · 110 lines · 111 tokens per session scan A 946afa3d103a

Subscribe to this mod's changes

human-handoff is a skill published in the GitHub repository Komdosh/komnet (7 stars, last pushed 5d ago), licensed MIT. It adds 111 tokens to every session and 1,239 once invoked, about $0.0006 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

writing-agent-relay-workflows

Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test hardening, channels…

AgentWorkforce/relay · 92 tokens

choosing-swarm-patterns

Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…

AgentWorkforce/relay · 76 tokens

relay-80-100-workflow

Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…

AgentWorkforce/relay · 121 tokens

creating-skills

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples.

AgentWorkforce/relay · 39 tokens

deploying-to-staging-environment

Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.

AgentWorkforce/relay · 44 tokens

github-oauth-nango-integration

Use when implementing GitHub OAuth + GitHub App authentication with Nango - provides two-connection pattern for user login and repo access with webhook handling.

AgentWorkforce/relay · 37 tokens