session-handoff

session-handoff is a skill for Claude Code, Codex from runnithan/claudex-setup. It costs 72 tokens per session (855 once invoked), scanned A, original, MIT.

A guide for writing a HANDOFF.md file that records the task, findings, failed attempts, commands, and remaining problems in a coding session. The file lets another tool or session continue with the same context.

In plain words
What is it for?
Use it to hand a difficult task from Claude Code to Codex or the other way around, preserve progress across restarts, and document what the next agent should try.
Why use it?
It prevents a replacement coding assistant from repeating investigations that have already been tried. This is useful when a problem is stuck, a session is ending, or work must move to another machine.

Skill for Claude CodeCodex

Part of the claudex-setup plugin — 3 skills, 21 commands, 22 agents shipped together

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/runnithan/claudex-setup/session-handoff
Any agent
npx skills add runnithan/claudex-setup --skill session-handoff
Clone the repo
git clone --depth 1 https://github.com/runnithan/claudex-setup

Made for: Claude Code, Codex.

Or install claudex-setup, the plugin that ships this one along with the rest of its 3 skills, 21 commands, 22 agents.

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 session-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/runnithan/claudex-setup/session-handoff.svg)](https://agentmods.dev/skills/runnithan/claudex-setup/session-handoff)
Your own site
<a href="https://agentmods.dev/skills/runnithan/claudex-setup/session-handoff"><img src="https://agentmods.dev/badge/skills/runnithan/claudex-setup/session-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 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 $0.00072 $0.00855
Opus 5 $0.00036 $0.00428
Sonnet 5 $0.00014 $0.00171
Haiku 4.5 $0.00007 $0.00085

Measured 4d ago against content hash c0ee21c87843, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-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 4d 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.

skills/session-handoff/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Handoff

Capture everything the other tool needs to continue this task, and write it to HANDOFF.md in the repo root.

The receiving tool starts cold. It has none of the conversation, none of the reasoning, and no memory of what has already been ruled out. Without a handoff it re-explores ground this session already closed, and its first suggestion is usually something tried an hour ago.

Use this when switching Claude Code to Codex or back, typically because a session is stuck. A different model is genuinely useful on a stuck problem, but only if it starts from where you got to.

When to use it

  • Two or more failed attempts at the same problem, where a differently-trained model is worth trying.
  • A long session about to be abandoned, whose reasoning is worth keeping.
  • Work that must continue on another machine or after a restart.

Not for routine context trimming. /compact or a fresh session with a plan file covers that. This is specifically for crossing a tool boundary.

What to write

Write HANDOFF.md with these sections. Be concrete and name real paths, commands and errors. Vagueness is what makes a handoff useless.

1. Task and definition of done

One paragraph on what is being attempted, then the finish line stated so it can be objectively checked. If the goal was fuzzy in this session, say so, because the receiving tool will otherwise invent a sharper one and solve the wrong problem.

2. Files in play

List each file touched or read closely, with one line on why it matters, not just that it was opened. A bare file list is close to worthless; the reason is the context.

3. Decisions made, and options rejected

Both halves. The rejected options matter more than the accepted ones: they are what a cold session re-litigates first, and re-arriving at a discarded approach wastes the entire benefit of the switch. For each rejection, record the reason, not just the verdict.

4. Current blocker

The precise failure. Paste the actual error text, the failing command, or the observed-versus-expected behaviour. Do not summarise an error message; the wording is often the clue.

Read the full file on GitHub · 63 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. 4d ago First seen · 63 lines · 72 tokens per session scan A c0ee21c87843

Subscribe to this mod's changes

session-handoff is a skill published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 855 once invoked, about $0.0004 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

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

ensure-pipelines-host

Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…

microsoft/power-platform-skills · 222 tokens