continuum-handoffs

continuum-handoffs is a skill for Claude Code, Codex from shyftlabs/continuum. It costs 98 tokens per session (1,872 once invoked), scanned A, original, Apache-2.0.

A handoff guide for letting one Continuum agent transfer a conversation to another specialist agent while controlling how much history is passed along.

In plain words
What is it for?
Use it to build triage systems, route billing or technical questions, summarize prior messages, detect cycles, and return to a parent agent.
Why use it?
It prevents every agent from having to handle every type of request and helps limit unnecessary conversation context.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/shyftlabs/continuum/continuum-handoffs
Any agent
npx skills add shyftlabs/continuum --skill continuum-handoffs
Clone the repo
git clone --depth 1 https://github.com/shyftlabs/continuum

Made for: Claude Code, Codex.

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 continuum-handoffs

README.md
[![agentmods](https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-handoffs.svg)](https://agentmods.dev/skills/shyftlabs/continuum/continuum-handoffs)
Your own site
<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-handoffs"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-handoffs.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00098 $0.01872
Opus 5 $0.00049 $0.00936
Sonnet 5 $0.00020 $0.00374
Haiku 4.5 $0.00010 $0.00187

Measured 2d ago against content hash ad6412788c80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

continuum-handoffs 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 2d 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.

.claude/skills/continuum-handoffs/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuum Handoffs Skill

Authoritative source: docs/agent.md, §7.

Handoffs are agent-to-agent transitions ("triage → billing"), distinct from workflow agents which compose multiple agents into one (Sequential, Parallel, etc.). Use a RouterAgent for stateless routing; use handoffs when the source agent should be able to decide at any turn that the target should take over.


Imports

from continuum.agent import BaseAgent, AgentRunner, Handoff
from continuum.agent.types import HistorySummarizationMode, HandoffData, HandoffResult
from continuum.agent.exceptions import (
    HandoffNotAllowedError, HandoffDepthExceededError,
    HandoffTargetNotFoundError,
)
# HandoffCycleDetectedError is NOT re-exported from `continuum.agent`:
from continuum.agent.exceptions import HandoffCycleDetectedError

Define a triage agent

billing   = BaseAgent(name="billing",   instructions="Help with invoices and refunds.")
technical = BaseAgent(name="technical", instructions="Help with bugs and outages.")

triage = BaseAgent(
    name="triage",
    instructions="Route the customer to the right specialist.",
    handoffs=[
        Handoff(target_agent="billing",
                description="Billing, payments, refunds, invoices"),
        Handoff(target_agent="technical",
                description="Bugs, errors, outages, integration issues"),
    ],
)

runner = AgentRunner(agent_registry={
    "triage": triage, "billing": billing, "technical": technical,
})
resp = await runner.run(triage, "I want a refund for invoice 1234",
                        user_id="u1", session_id="s1")
print(resp.handoff_chain)            # ["triage", "billing"]
print(resp.content)                  # the billing agent's reply

Handoff fields

Field Type Default Purpose
target_agent str required Name of the target agent
description str required When this handoff should fire — read by the LLM
condition str | Callable | None None Extra guard (rarely used)
transfer_history bool True Pass conversation history to the target
summarize_history bool True Run an LLM summarization before transferring
summarization_mode HistorySummarizationMode HYBRID See table below
recent_messages int 5 Used by RECENT_N and HYBRID
return_to_parent bool True After the target finishes, control returns to the source

Read the full file on GitHub · 206 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. 2d ago First seen · 206 lines · 98 tokens per session scan A ad6412788c80

Subscribe to this mod's changes

continuum-handoffs is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 2d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,872 once invoked, about $0.0005 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 2026-09-03.