handoff

handoff is a skill for Claude Code, Codex from PVRLabs/aibadger. It costs 35 tokens per session (403 once invoked), scanned A, original, MIT.

A guide for packaging the current coding session so another AI agent, AI Badger, can continue it. The handoff records goals, decisions, progress, blockers, and next steps.

In plain words
What is it for?
Use it to transfer an ongoing coding, debugging, planning, or architecture session to AI Badger.
Why use it?
It prevents important conversation context from being lost when work moves to another agent or terminal.

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/pvrlabs/aibadger/handoff
Any agent
npx skills add PVRLabs/aibadger --skill handoff
Clone the repo
git clone --depth 1 https://github.com/PVRLabs/aibadger

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 handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/pvrlabs/aibadger/handoff.svg)](https://agentmods.dev/skills/pvrlabs/aibadger/handoff)
Your own site
<a href="https://agentmods.dev/skills/pvrlabs/aibadger/handoff"><img src="https://agentmods.dev/badge/skills/pvrlabs/aibadger/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 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 $0.00035 $0.00403
Opus 5 $0.00017 $0.00201
Sonnet 5 $0.00007 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured yesterday against content hash a419b6c2a678, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/handoff/SKILL.md · 54 lines

What it actually says

Badger Handoff

Create .badger-handoff in the current working directory, or another workspace directory explicitly selected by the user. Do not discover a Git root.

Summarize the session concisely and with high information density. Preserve enough context to continue without repeating investigation or misunderstanding a decision. Give later decisions and corrections precedence.

Remove conversational noise, repetition, obsolete details, and information Badger can recover from the repository. Preserve the current goal, material progress, decisions and rationale, constraints and non-goals, completed work, verification results, significant failed approaches, blockers, and immediate next steps. Include exact details only when they are necessary for continuity.

Aim for no more than 2,000 output tokens under normal circumstances. Use less for simple sessions. Exceed this target only when further compression would discard continuation-critical information.

Use mode: handoff when repository work is part of the session. Use mode: design only for reasoning where current worktree state is irrelevant. Write this exact UTF-8 framing:

BADGER-HANDOFF-V1
mode: handoff

<compact session summary>

Keep the complete file at or below 65,536 bytes. The body is conversation state only: do not inspect or include repository files, diffs, Git state, or topology. Badger collects repository context itself.

After writing successfully, derive the absolute directory from the written file path and print exactly:

Badger handoff prepared.

In a separate terminal, run:

cd '/absolute/path/to/the-written-directory'
badger continue

Substitute the actual POSIX-shell-quoted directory. Do not invoke Badger or use another transport.

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. yesterday Changed · +9 lines a419b6c2a678
  2. 5d ago First seen · 45 lines · 35 tokens per session scan A fa52bab9cdbc

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository PVRLabs/aibadger (30 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 403 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.