Handoff

What it does

When your agent uses it

• Switching focus
• Ending sessions
• Splitting work across sessions

Example prompts

• “/handoff”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Describe state. Write "Auth is implemented; logout is not started," not "Implement logout next." The next agent chooses actions from the…
2. 2Link existing artifacts. Reference PRDs, plans, ADRs, issues, commits, diffs, and design docs by path or URL instead of copying their…
3. 3Preserve why. Capture decisions, rejected approaches, and failures that code alone cannot explain.
4. 4Require verification. Present claims as context to check against the actual code, not facts to trust blindly.
5. 5Redact secrets and PII. Never include keys, tokens, passwords, or personal data. Name credential locations (e.g. ".env.local, not…
6. 6Keep only useful context. Omit obvious, redundant, or explanatory material recoverable from code or project configuration.

What it can do on your machine

Read from SKILL.md and the folder at commit 7874889. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Handoff loads about 1.1k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~38

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:18

  l data. Name credential locations (e.g. ".env.local, not committed"), never values.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davidondrej/skills at commit 7874889, republished under its MIT licence (© davidondrej). 261 words, ~1,057 tokens.

name

handoff

description

Capture session context for a fresh agent. Use for handoffs, context limits, switching focus, ending sessions, or splitting work across sessions.

disable-model-invocation

true

triggers

user, model

# HANDOFF: <short title of the work>
Generated: <timestamp> · Session focus: <one line>

## 1. Goal
<The overall objective in 1–3 sentences.>

## 2. Why This Matters / Background
<Motivation, intended users, timing, constraints, and hard requirements not already in project configuration.>

## 3. Current State
<What is DONE, PARTIAL, and NOT STARTED. Describe status, not actions:
- DONE: OAuth login flow, tests passing locally
- PARTIAL: Session storage wired up; refresh logic missing
- NOT STARTED: Logout endpoint>

## 4. Key Decisions (and why)
<Choices and reasoning, especially what cannot be recovered from code.
- Chose passport.js over custom OAuth — community support and less surface area
- Stored tokens in httpOnly cookies — XSS mitigation>

## 5. Traps & Dead Ends
<Failed approaches and pitfalls the next agent might repeat, with reasons.
- DB mocks made integration tests flaky; replaced with a test container
- SDK v3 breaks the streaming API this project relies on>

## 6. Relevant Files & Pointers
<Paths with line ranges and specific contents; link external artifacts instead of copying them.
- src/auth/oauth.ts:L40-L88 — provider config + token exchange
- docs/adr/0007-auth.md — full rationale
- PR #142 — in-progress session work
- Issue #150 — logout requirements>

## 7. Open Work (status, with dependencies)
<Remaining work and dependencies, stated as status rather than commands.
- Logout endpoint is not implemented
- Session persistence depends on the logout endpoint
- E2E auth tests are blocked until both are complete>

---
## Prompt for the Fresh Agent
<A short prompt with background context. Use declarative statements such as "X is complete" or "Y has not started." Preserve this exact closing instruction:>

Before responding, read every file listed under "Relevant Files & Pointers" above.
Do not summarize, paraphrase, or claim you already have context — actually read each
file. Treat every claim in this handoff as context to verify against the code, not
facts to trust blindly. Then wait for my instructions before taking any action.

Read the file <absolute-path> to get the context, then wait for instructions.

© davidondrej, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/agent-orchestration/handoff of davidondrej/skills.

• SKILL.md
• agents/openai.yaml

Open the folder on GitHubat commit 7874889