agentmods.dev

handoff-task

handoff-task is a skill for Claude Code, Codex from hoangsonww/AI-Agents-Orchestrator. It costs 31 tokens per session (187 once invoked), scanned A, original, MIT.

A coding-task handoff procedure for passing verified work from one AI coding agent to another. It records the repository state, changed files, test results, decisions, and a clear next action.

In plain words
What is it for?
Use it when another agent must continue a task. It helps inspect the current Git branch and diff, save a checkpoint, and produce a compact continuation note without committing or pushing.
Why use it?
It reduces the risk that the next agent relies on outdated conversation history or misunderstands what was actually changed. It also prevents unsupported claims about tests or unfinished work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ai-collaboration plugin — 5 skills shipped together

not rated 99repo +2 1mo ago A scan 31 tokens original MIT

Good fit Use it when another agent must continue a task. It helps inspect the current Git branch and diff, save a checkpoint, and produce a compact continuation note without committing or pushing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangsonww/ai-agents-orchestrator/handoff-task
View source ↗ hoangsonww/AI-Agents-Orchestrator hoangsonww.github.io
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 hoangsonww/AI-Agents-Orchestrator --skill handoff-task
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-Agents-Orchestrator

Made for: Claude Code, Codex.

Or install ai-collaboration, the plugin that ships this one along with the rest of its 5 skills.

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 handoff-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/ai-agents-orchestrator/handoff-task/github.svg)](https://agentmods.dev/skills/hoangsonww/ai-agents-orchestrator/handoff-task)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/ai-agents-orchestrator/handoff-task"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-agents-orchestrator/handoff-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handoff-task

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/ai-agents-orchestrator/handoff-task"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-agents-orchestrator/handoff-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 187 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 $0.00031 $0.00187
Opus 5.5 $0.00012 $0.00075
Sonnet 5.5 $0.00006 $0.00037
Haiku 4.5 $0.00003 $0.00019

Measured 1mo ago against content hash 32555298b062, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

handoff-task 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 1mo 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.

AI-Collaboration-Skills/skills/handoff-task/SKILL.md · 16 lines

What it actually says

Handoff Task

Use this skill only when the user requests a handoff or asks another agent to continue.

  1. Call ai_collaboration.get_context and inspect the actual Git diff.
  2. Resolve discrepancies between current files and captured history in favor of current repository state.
  3. Record a checkpoint with ai_collaboration.record_checkpoint containing completed work, remaining work, decisions, known failures, and one concrete next action.
  4. Return a compact handoff containing the task ID, repository and branch, changed files, tests, checkpoint, and suggested first action.

Do not commit, push, open a pull request, or mark the task complete unless the user explicitly requested those actions. Do not include raw secrets or unnecessary transcript content.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 16 lines · 31 tokens per session scan A 32555298b062

Subscribe to this mod's changes

handoff-task is a skill published in the GitHub repository hoangsonww/AI-Agents-Orchestrator (99 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 187 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.

Building agentsGit and workflowagentic-aiai-agentsclaudecodexcopilotdocker
Related

handoff-task compared with skills from other repositories

handoff-task next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
handoff-taskhoangsonww/AI-Agents-OrchestratorSkill991mo agoMITA31Claude Code, Codex
github-review-prfeiskyer/claude-code-settingsSkill1.7k2d agoMITA90Claude Code
github-fix-issuefeiskyer/claude-code-settingsSkill1.7k2d agoMITA42Claude Code
respond-to-pr-commentsmicrosoft/PromptKitSkill11310d agoMITA62Claude Code, Codex
github-review-prfeiskyer/codex-settingsSkill2482d agoMITA28Codex
apex-github-operationsjonathan-vella/apex-acceleratorSkill502d agoMITA96Claude Code
container-manager-gitops-persistKnuckles-Team/container-manager-mcpSkill6yesterdayMITA146Claude Code, Codex