handoff

handoff is a skill for Claude Code from Bidiche49/claude-conf. It costs 15 tokens per session (1,404 once invoked), scanned B, original, MIT.

A session handoff tool that saves the current work and creates a prompt for continuing it in a new conversation.

In plain words
What is it for?
Use it to record project context, progress, technical decisions, changed files, and unanswered user questions for the next session.
Why use it?
It reduces the risk of losing decisions, completed work, open questions, and remaining tasks when a conversation ends.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to record project context, progress, technical decisions, changed files, and unanswered user questions for the next session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bidiche49/claude-conf/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 Bidiche49/claude-conf --skill handoff
Clone the repo
git clone --depth 1 https://github.com/Bidiche49/claude-conf

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 handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/bidiche49/claude-conf/handoff/github.svg)](https://agentmods.dev/skills/bidiche49/claude-conf/handoff)
Your own site
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/handoff"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/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 handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/handoff"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 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 $0.00015 $0.01404
Opus 5.5 $0.00006 $0.00562
Sonnet 5.5 $0.00003 $0.00281
Haiku 4.5 $0.00002 $0.00140

Measured 1mo ago against content hash ef815645f6af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

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 1mo 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.

cat ~/.claude/handoff-system/pending/{SESSION_ID}.txt 2>/dev/null
handoff-kit/skills/handoff/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systeme de Handoff - Sauvegarde de Session

Tu es le gestionnaire de handoff. Ta mission est de sauvegarder l'etat complet de la session actuelle et generer un prompt optimise pour continuer dans une nouvelle conversation.

Workflow

0. VERIFIER LA QUESTION EN ATTENTE

IMPORTANT: Avant tout, verifie s'il y a une question utilisateur en attente:

# Lire la question en attente (si existe)
cat ~/.claude/handoff-system/pending/{SESSION_ID}.txt 2>/dev/null

Si un fichier existe, cette question doit etre incluse dans le prompt de continuation car l'utilisateur l'a posee juste avant le handoff et n'a pas eu de reponse.

1. COLLECTER LE CONTEXTE

Analyse la conversation actuelle et extrait:

Informations de base:

  • Nom du projet (depuis le chemin de travail)
  • Ticket lie (BUG-XXX, FEAT-XXX, IMP-XXX si mentionne)
  • Date/heure du handoff
  • Objectif principal de la session

Progression:

  • Liste des taches completees (avec details)
  • Tache en cours (avec etat actuel)
  • Taches restantes
  • Pourcentage de progression estime

Decisions techniques:

  • Choix d'implementation faits
  • Raisons de ces choix
  • Alternatives ecartees

Fichiers:

  • Fichiers crees ou modifies
  • Type de modification (creation, edit, suppression)
  • Extraits de code cles (si pertinent)

Contexte technique:

  • Patterns utilises
  • Dependances ajoutees
  • Configurations modifiees
  • Erreurs rencontrees et solutions

Blocages:

  • Problemes non resolus
  • Questions en suspens
  • Points d'attention

2. GENERER LE FICHIER DE PROGRESSION

Cree le fichier de progression avec un ID unique base sur timestamp:

Emplacement local: .claude-sessions/HANDOFF-{TIMESTAMP}.md Emplacement global: ~/.claude/handoff-system/sessions/{PROJECT}-{TIMESTAMP}.md

Format du fichier (rempli avec les vraies donnees):

# Session Progress - HANDOFF-{TIMESTAMP}

**Projet:** {nom du projet}
**Date debut:** {estime depuis contexte}
**Date handoff:** {maintenant}
**Ticket lie:** {TICKET-XXX ou "Aucun"}

---

## Objectif de la session

{description claire de ce que l'utilisateur voulait accomplir}

---

## Etat actuel

### Progression globale
{X}% complete

### Ce qui a ete fait
- {tache 1 completee avec details}
- {tache 2 completee avec details}
- ...

### Ce qui reste a faire
- {tache restante 1}
- {tache restante 2}
- ...

---

## Decisions prises

| Decision | Raison | Impact |
|----------|--------|--------|
| {decision 1} | {raison} | {fichiers affectes} |
| {decision 2} | {raison} | {fichiers affectes} |

---

## Fichiers modifies

| Fichier | Type | Statut |
|---------|------|--------|
| `path/to/file1` | Modifie | OK |
| `path/to/file2` | Cree | OK |

---

## Code cle

{uniquement si necessaire pour la reprise}

---

## Blocages / Points d'attention

{liste des problemes ou questions}

---

## Prochaines etapes

1. {action immediate suivante}
2. {action suivante}
3. {action suivante}

---

## Commandes utiles

{commandes bash utiles pour reprendre}

Read the full file on GitHub · 221 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. 1mo ago First seen · 221 lines · 15 tokens per session scan B ef815645f6af

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,404 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 2026-08-31.