handoff

handoff is a skill for Claude Code, Codex from johardi/claude-stack. It costs 172 tokens per session (1,001 once invoked), scanned A, original, MIT.

A handover procedure for returning an agent's isolated worktree branch to a person. A worktree is a separate working copy of a Git project, and the procedure prepares it for someone else to continue.

In plain words
What is it for?
Use it when a person asks to take over an agent's branch, review its files, or run the project locally. It handles committing, stashing, or discarding changes and can optionally push the branch.
Why use it?
It prevents unfinished changes from being left in an unclear state when a person wants to inspect or continue the work. It can record the handover and provide the next steps.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/johardi/claude-stack/handoff
Any agent
npx skills add johardi/claude-stack --skill handoff
Clone the repo
git clone --depth 1 https://github.com/johardi/claude-stack

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/johardi/claude-stack/handoff.svg)](https://agentmods.dev/skills/johardi/claude-stack/handoff)
Your own site
<a href="https://agentmods.dev/skills/johardi/claude-stack/handoff"><img src="https://agentmods.dev/badge/skills/johardi/claude-stack/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,001 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 $0.00172 $0.01001
Opus 5 $0.00086 $0.00500
Sonnet 5 $0.00034 $0.00200
Haiku 4.5 $0.00017 $0.00100

Measured 3d ago against content hash c43a74db948d, 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 3d 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/cstack-collab/skills/handoff/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

The agent is standing in an isolated worktree (created by Agent({isolation: "worktree"}) or by cstack-collab orchestration). The human wants to take the branch over locally — review the actual files, run a dev server, etc. — without waiting for a PR merge or the harness's automatic worktree reaping.

This skill is the agent's "I'm yielding" ritual. It does not remove the worktree (the agent is standing in it); it puts the branch in a state where the human can pick it up cleanly via /cstack-collab:reclaim.

When to Use

Use when:

  • The human types /cstack-collab:handoff (with optional flags).
  • The human says something equivalent during an active agent session: "let's hand off", "I'll take over", "wrap up so I can check out the branch", "finish cleanly".

Skip when:

  • Not inside a Claude agent worktree. The script will refuse anyway, but recognize this up front and route the human to /cstack-collab:reclaim instead.
  • The human is asking the agent to commit its work but keep working — that's just a normal commit, not a handoff.

Inputs

The human may pass any of these (interpret natural language too — e.g., "stash my changes" → --stash):

Flag Meaning
--commit "<msg>" Commit dirty state on the current branch with this message. Default if you can derive a meaningful message from the conversation.
--stash Preserve dirty state at refs/cstack-collab/handoff/<agent-id> instead of committing.
--discard Throw the dirty state away.
--no-push Skip the git push -u origin <branch> step. Default is to push.
--summary "<text>" One-line summary recorded in state.json events (orchestration only).

If the tree is dirty and none of --commit, --stash, --discard is supplied, the script refuses. Do not silently pick one for the user — ask them which they want, citing the changed files.

How to Run

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/handoff.py" [flags]

The script:

  1. Refuses if not inside a Claude agent worktree.
  2. Handles dirty state per the flag (commit / stash / discard).
  3. Best-effort git push -u origin <branch> (override with --no-push).
  4. Appends a handoff event to state.json if an orchestration is active.
  5. Prints the exact /cstack-collab:reclaim invocation the human should run from their primary repo.

Read the full file on GitHub · 65 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. 3d ago First seen · 65 lines · 172 tokens per session scan A c43a74db948d

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository johardi/claude-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 172 tokens to every session and 1,001 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens