agent-task-handoff

agent-task-handoff is a skill for Claude Code, Codex from aiming-lab/MetaClaw. It costs 46 tokens per session (231 once invoked), scanned A, original, MIT.

A handoff guide for giving a sub-agent or another work session enough information to complete a delegated task.

In plain words
What is it for?
Use it to write task handoffs containing the goal, context, constraints, inputs, ownership, merge instructions, and success checks.
Why use it?
It prevents the receiving agent from having to reconstruct missing context or guess what constraints and files matter.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to write task handoffs containing the goal, context, constraints, inputs…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiming-lab/metaclaw/agent-task-handoff
About the project

MetaClaw is an AI-agent system that learns from conversations and evolves its behavior over time. It provides memory and learning modes for users who want an agent that adapts across interactions, with support for multiple claw-based agent projects.

aiming-lab/MetaClaw · 3,496 stars · on GitHub · arxiv.org

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 aiming-lab/MetaClaw --skill agent-task-handoff
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/MetaClaw

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 agent-task-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiming-lab/metaclaw/agent-task-handoff.svg)](https://agentmods.dev/skills/aiming-lab/metaclaw/agent-task-handoff)
Your own site
<a href="https://agentmods.dev/skills/aiming-lab/metaclaw/agent-task-handoff"><img src="https://agentmods.dev/badge/skills/aiming-lab/metaclaw/agent-task-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 231 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 $0.00046 $0.00231
Opus 5 $0.00023 $0.00115
Sonnet 5 $0.00009 $0.00046
Haiku 4.5 $0.00005 $0.00023

Measured 7d ago against content hash 8686b5fdb224, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-task-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 7d 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.

memory_data/skills/agent-task-handoff/SKILL.md · 23 lines

What it actually says

Agent Task Handoff

When delegating work to a sub-agent or across sessions, make the handoff self-contained.

Handoff package must include:

  1. Goal: What the sub-agent must produce (one clear sentence).
  2. Context: The minimum background the agent needs — no more, no less.
  3. Constraints: Explicit rules (don't modify X, use library Y, output format Z).
  4. Inputs: File paths, API endpoints, or data the agent needs to start.
  5. Success criteria: How to verify the result is correct.

For parallel agents:

  • Clearly state which parts of the codebase/data each agent owns.
  • Define how outputs will be merged back.

Anti-pattern: Sending a vague "continue where we left off" with no context — sub-agents start from zero.

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. 7d ago First seen · 23 lines · 46 tokens per session scan A 8686b5fdb224

Subscribe to this mod's changes

agent-task-handoff is a skill published in the GitHub repository aiming-lab/MetaClaw (3,496 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 231 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

Training

Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.

agentic-in/elephant-agent · 23 tokens

llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.

davila7/claude-code-templates · 51 tokens

tinker-fine-tuning

Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.

synthetic-sciences/openscience · 62 tokens

tinker-training-cost

Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

synthetic-sciences/openscience · 55 tokens

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

colab-finetuning

Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.

synthetic-sciences/openscience · 67 tokens