core-handoff

core-handoff is a skill for Claude Code, Codex from LiXin97/agora-lab. It costs 21 tokens per session (207 once invoked), scanned A, original, Apache-2.0.

A handoff protocol for sending another coding agent a file, request, success condition, blocker, or dependency.

In plain words
What is it for?
Use it to request reviews, transfer artifacts, ask for help with decisions, hand over next steps, and record these messages in shared files.
Why use it?
It makes cross-agent work specific and traceable, so the receiving agent knows exactly what to do and what result is expected.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to request reviews, transfer artifacts, ask for help with decisions, hand over next steps, and record these messages in shared files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lixin97/agora-lab/core-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 LiXin97/agora-lab --skill core-handoff
Clone the repo
git clone --depth 1 https://github.com/LiXin97/agora-lab

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 core-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/lixin97/agora-lab/core-handoff/github.svg)](https://agentmods.dev/skills/lixin97/agora-lab/core-handoff)
Your own site
<a href="https://agentmods.dev/skills/lixin97/agora-lab/core-handoff"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/core-handoff/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 core-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/lixin97/agora-lab/core-handoff"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/core-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 207 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 $0.00021 $0.00207
Opus 5 $0.00010 $0.00103
Sonnet 5 $0.00004 $0.00041
Haiku 4.5 $0.00002 $0.00021

Measured 9d ago against content hash 6f6595f19b84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

core-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 9d 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/core-handoff/SKILL.md · 38 lines

What it actually says

Core Handoff

Every cross-agent request should include:

  1. the artifact or file path
  2. the exact request
  3. the success condition
  4. the blocking question, if any
  5. the downstream dependency, if any

Message Pattern

Use the canonical shared message directory from your AGENTS/CLAUDE instructions when one agent needs another to:

  • review an artifact
  • unblock a decision
  • inspect a result
  • take over a next step

Name the file {from}_to_{recipient}_{timestamp}_{type}.md and include frontmatter with:

---
from: <sender>
to: <recipient|all>
type: <instruction|question|review|notification>
timestamp: <ISO 8601>
status: unread
---

Keep the request narrow enough that the receiver can act without re-deriving the objective.

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. 9d ago First seen · 38 lines · 21 tokens per session scan A 6f6595f19b84

Subscribe to this mod's changes

core-handoff is a skill published in the GitHub repository LiXin97/agora-lab (49 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 207 once invoked, about $0.0001 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.