A session handoff procedure that records the current coding session in HANDOFF.md. It gathers Git status, recent commits, the branch, and test results.

Use it before clearing the session to document unfinished work, changed files, recent decisions, and test status.

It preserves the work state so another session can continue without reconstructing what happened.

How johnnichev/selectools configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to johnnichev/selectools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/johnnichev/selectools/main/.claude/skills/handoff/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/johnnichev/selectools

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/johnnichev/selectools/handoff/github.svg)](https://agentmods.dev/skills/johnnichev/selectools/handoff)

Your own site

<a href="https://agentmods.dev/skills/johnnichev/selectools/handoff"><img src="https://agentmods.dev/badge/skills/johnnichev/selectools/handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/johnnichev/selectools/handoff"><img src="https://agentmods.dev/badge/skills/johnnichev/selectools/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 302 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00302
Opus 5.5	$0.00009	$0.00121
Sonnet 5.5	$0.00005	$0.00060
Haiku 4.5	$0.00002	$0.00030

Measured 2mo ago against content hash bca0928a6665, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.claude/skills/handoff/SKILL.md · 42 lines

What it actually says

Session Handoff

Auto-fill HANDOFF.md with the current session state so the next session can resume.

Steps

Run git status --short to find modified/untracked files
Run git log --oneline -5 to get recent commits
Run git branch --show-current to get current branch
Run python3 -m pytest tests/ -x -q --tb=no 2>&1 | tail -1 to check test status
Write HANDOFF.md with:

# Session Handoff

## What I Was Doing
[Summarize from conversation context - what was the user working on?]

## Current State
- Branch: [from git branch]
- Last commit: [from git log]
- Tests passing: [from pytest output]
- Files in progress: [from git status]

## What's Left
1. [Infer from conversation - what hasn't been done yet?]

## Key Decisions Made
- [List decisions from this session that aren't in the code]

## Watch Out For
- [Any gotchas or context that would be lost]

Tell the user: "HANDOFF.md updated. Run /clear to start fresh. The next session will read HANDOFF.md automatically."

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.

2mo ago First seen · 42 lines · 23 tokens per session scan A bca0928a6665

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 23 tokens to every session and 302 once invoked, about $0.0001 per session on Opus 5.5. 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.

AI Safety Git and workflow Guardrails Memory and context ai-agents anthropic enterprise-ai gemini

handoff next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
handoffjohnnichev/selectools	Skill	11	4d ago	Apache-2.0	A	23	Claude Code
llamaguarddavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	74	Claude Code, Codex
releaseBlockRunAI/ClawRouter	Skill	6.7k	yesterday	MIT	A	44	Claude Code, Codex
releasedevoxx/DevoxxGenieIDEAPlugin	Skill	687	yesterday	MIT	A	121	Claude Code
close-task-commit-push-prdevoxx/DevoxxGenieIDEAPlugin	Skill	687	yesterday	MIT	A	64	Claude Code
git-commit-push-prdevoxx/DevoxxGenieIDEAPlugin	Skill	687	yesterday	MIT	A	53	Claude Code
start-taskdevoxx/DevoxxGenieIDEAPlugin	Skill	687	yesterday	MIT	A	54	Claude Code

selectools: Skill for Claude Code