repo-handoff

repo-handoff is a skill for Claude Code from rjwalters/kicad-tools. It costs 35 tokens per session (3,647 once invoked), scanned B, original, MIT.

A session handoff routine that records unfinished work, restores a clean Git starting point, checks for command-line updates, and writes restart notes for the next coding session.

In plain words
What is it for?
Use it before closing or restarting a session to capture follow-up tasks, return the repository to a known baseline, and tell the next session what to read first.
Why use it?
Important decisions and discoveries can be lost when a coding session ends or the tool is updated. It makes restarting a repeatable process instead of relying on memory.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it before closing or restarting a session to capture follow-up tasks, return the repository to a known baseline, and tell the next session what to read first.

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

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.

agentmods badge for repo-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-handoff/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/repo-handoff)
Your own site
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-handoff"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-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.

agentmods 80×15 button for repo-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-handoff"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,647 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00035 $0.03647
Opus 5.5 $0.00014 $0.01459
Sonnet 5.5 $0.00007 $0.00729
Haiku 4.5 $0.00003 $0.00365

Measured 8d ago against content hash 06df50cc6c55, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

repo-handoff scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

# After relaunching, read it yourself: cat .claude/handoff.md
.agents/skills/repo-handoff/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex form of the /repo:handoff command. Other commands appear as $repo-<verb> skills. Helper scripts and .claude/ paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.

$repo-handoff — Roll the Session Safely

Rolling a Claude Code session — quitting the CLI and starting fresh — is the moment a session's most valuable output is most likely to be lost, because what is worth carrying forward is exactly what exists only in the session's context: in-flight state, settled decisions, and empirically-discovered traps. This command makes the roll a repeatable ritual instead of an ad-hoc scramble.

It composes the existing commands rather than reimplementing them — [[followups]] to capture deferred work, [[reset]] to reach a clean git baseline — and adds only what does not exist yet: the CLI version check, the handoff note, and exact restart instructions.

Relationship to /compact: compaction handles the soft boundary — context pressure within a continuous session. $repo-handoff handles the hard boundary: process restart, CLI upgrade, or a deliberate fresh start. If the version check below finds no update and the only pressure is context size, say so — a /compact may be all that's needed.

Usage

$repo-handoff                  # Run the ritual end-to-end, confirmations as usual
$repo-handoff --dry-run        # Preview the note and proposed actions; file, prune, and write nothing
$repo-handoff --prune          # Pass --prune through to the reset stage
$repo-handoff --force          # Proceed even when the step-0 preflight fails

Steps — ordering is load-bearing

Run the stages in exactly this order. Each later stage depends on the earlier ones having actually happened.

0. Preflight — confirm something will actually read the note

Read the full file on GitHub · 303 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. 8d ago First seen · 303 lines · 35 tokens per session scan B 06df50cc6c55

Subscribe to this mod's changes

repo-handoff is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 3,647 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

Related

repo-handoff compared with skills from other repositories

repo-handoff next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-handoffrjwalters/kicad-toolsSkill73yesterdayMITB35Claude Code
Dotfilesdanielmiessler/LifeOSSkill20k4d agoMITA125Claude Code, Codex
conventional-commitJanDeDobbeleer/oh-my-poshSkill24kyesterdayMITA26Claude Code, Codex
python-releaseComposioHQ/composioSkill31ktodayMITA53Claude Code, Codex
release-noteskenryu42/cc-safety-netSkill2.0kyesterdayMITA65Claude Code, Codex
ratchet-filesdzhng/skillsSkill1.5kyesterdayMITA118Claude Code, Codex
git-guardrails-claude-codevinvcn/mattpocock-skills-zh-CNSkill5.6k12d agoMITB68Claude Code, Codex