handoff

handoff is a skill for Claude Code from Angel45604/the-foreman. It costs 143 tokens per session (1,851 once invoked), scanned A, original, MIT.

A session handoff package for passing unfinished coding work to a new agent. It creates a detailed handoff document and a short prompt that tells the next agent where to start.

In plain words
What is it for?
Use it when coding work is incomplete and another agent must continue it. It helps transfer the project's state, workflow, and remaining tasks.
Why use it?
It prevents important context, current work, checks, and known problems from being lost when a session runs out of context.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Codex.

Part of the the-foreman plugin — 5 skills shipped together

Good fit Use it when coding work is incomplete and another agent must continue it. It helps transfer the project's state, workflow, and remaining tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/angel45604/the-foreman/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 Angel45604/the-foreman --skill handoff
Clone the repo
git clone --depth 1 https://github.com/Angel45604/the-foreman

Made for: Claude Code.

Or install the-foreman, 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/angel45604/the-foreman/handoff.svg)](https://agentmods.dev/skills/angel45604/the-foreman/handoff)
Your own site
<a href="https://agentmods.dev/skills/angel45604/the-foreman/handoff"><img src="https://agentmods.dev/badge/skills/angel45604/the-foreman/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,851 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 $0.00143 $0.01851
Opus 5 $0.00072 $0.00925
Sonnet 5 $0.00029 $0.00370
Haiku 4.5 $0.00014 $0.00185

Measured 8d ago against content hash 7c572eed5098, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

plugin/skills/handoff/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

handoff — teach the next agent (cold-start handoff + kickoff prompt)

The next agent starts with zero context. Your job is not to summarize — it's to transmit enough that a fresh agent resumes as if it were you: the same understanding of the work, the same git/verification footing, and the same development workflow (skills, posture, hard-won gotchas).

You produce two artifacts at two altitudes, and they are different on purpose:

Artifact Altitude Audience Filename (default)
Handoff doc deep, exhaustive the fresh agent reads it cold handoff-<YYYY-MM-DD>-<slug>.md
Kickoff prompt lean, paste-ready the user pastes it into the fresh agent next-agent-prompt-<YYYY-MM-DD>-<slug>.md

The kickoff prompt points at the handoff doc — it never duplicates it. The user copies the kickoff prompt in one action; the fresh agent then reads the doc for the full picture.


Step 1 — Gather ground truth (never write a handoff from memory)

A handoff is a pile of claims about state. A wrong claim sends the fresh agent down the wrong path for an hour. Anchor everything in evidence before you write a word:

  • Git state — run git status -sb, git log --oneline -8, git branch --show-current, git rev-parse HEAD. Capture: branch, exact HEAD sha, clean vs dirty, staged vs unstaged, pushed vs local-only, and anything that must never be staged (scratch, design bundles, dev hacks).
  • Verification — list the test / lint / build commands this work uses and their last actual result. Tag each ✅ verified this session vs ⬜ assumed. Never mark work DONE that you didn't watch pass — an honest "in-flight, unverified" beats a confident lie.
  • Where the work lives — the active plan/bundle dir (docs/plans/active/...), the key files as path:line, the auto-memory entry if the project uses one.
  • The conversation — distill: the goal + why, decisions already made, gotchas discovered, what's DONE+verified, what's in-flight, and the exact next steps in order.

Read the full file on GitHub · 112 lines

Files

What ships with it

2 files 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. 8d ago First seen · 112 lines · 143 tokens per session scan A 7c572eed5098

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository Angel45604/the-foreman (2 stars, last pushed 9d ago), licensed MIT. It adds 143 tokens to every session and 1,851 once invoked, about $0.0007 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.