handoff

A handover workflow for documenting an AI-built application so another developer can take over. It covers setup, deployment, environment variables, design decisions, code structure, and known limitations.

In plain words
What is it for?
Use it before giving an app to a client, contractor, teammate, or your future self. It helps test a fresh setup, write an honest README, record decisions, and map the codebase.
Why use it?
It removes the need to rely on the original developer's memory and reveals setup steps or assumptions that would otherwise block future work.

Skill for Claude CodeCodex

Part of the vibe-stack plugin — 14 skills, 1 command, 1 agent shipped together

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/onewave-ai/open-agent-stack/handoff
Any agent
npx skills add OneWave-AI/open-agent-stack --skill handoff
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack

Made for: Claude Code, Codex.

Or install vibe-stack, the plugin that ships this one along with the rest of its 14 skills, 1 command, 1 agent.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 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 $0.00060 $0.00568
Opus 5 $0.00030 $0.00284
Sonnet 5 $0.00012 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 2d ago against content hash 9ab9fa9ce89e, 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 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.

plugins/vibe-stack/skills/handoff/SKILL.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

The app works and only one person knows why. That is fine until it is a client deliverable, a contractor's starting point, or a Monday six months from now. Handoff is the pass that moves the knowledge out of the head and into the repo.

Workflow

  1. Prove the cold start. Clone into a fresh directory and follow your own setup instructions exactly as written -- no memory, no shortcuts. Every step that fails or requires unwritten knowledge is a documentation bug. This single test catches most of what handoff docs get wrong.
  2. Write the honest README. What the app does in two sentences, the stack, how to run it, how to deploy it, what every environment variable is and where to get its value. Then the sections people leave out: what is stubbed, what is intentionally simple, and what will break first under load.
  3. Record the decisions. A short DECISIONS.md: why this database, why this auth, why the odd-looking workaround in that one file. Undocumented decisions get "cleaned up" by the next developer, and then the bug they were preventing comes back.
  4. Map the code. A brief tour: where routes live, where shared components live, where the data layer is, and the two or three files that matter most. New developers do not need every file explained -- they need to know where to start reading.
  5. Hand over the keys, safely. Inventory every account and service the app depends on (hosting, database, domain, email, payments, analytics) with who owns it today and what has to transfer. Credentials move through a secure channel, never the repo, never chat. Rotate anything that has been shared loosely.

Rules

  • Document what is true today, not the roadmap. Aspirational docs are worse than none because they get trusted.
  • Every known gap gets written down. A listed shortcut is a decision; a hidden one is a trap.
  • Delete dead code and unused dependencies before handing over -- the new developer cannot tell what is load-bearing and will preserve all of it.
  • Setup instructions that only work on your machine are not instructions. If it needs a specific version, pin it and say so.
  • If the app is going to a client, include the plain-language answer to "what can I change safely myself" -- copy, images, content -- and what needs a developer.

Read the full file on GitHub · 25 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 · 25 lines · 60 tokens per session scan A 9ab9fa9ce89e

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 22d ago), licensed MIT. It adds 60 tokens to every session and 568 once invoked, about $0.0003 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 2026-08-31.