superforge-handoff

superforge-handoff is a skill for Claude Code from takaoumehara/superforge-skill. It costs 229 tokens per session (1,584 once invoked), scanned A, original, MIT.

A session handoff format that saves the current project state in a structured file so another AI model or tool can continue the work. It is intended for switching tools or ending a long session.

In plain words
What is it for?
Use it before changing models or coding tools, clearing a long chat, or passing work to an asynchronous agent such as Devin.
Why use it?
It preserves decisions, files, running processes, open questions, and next steps when the new tool does not have the earlier conversation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the superforge-skills plugin — 15 skills shipped together

Good fit Use it before changing models or coding tools, clearing a long chat, or passing work to an asynchronous agent such as Devin.

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

Made for: Claude Code.

Or install superforge-skills, the plugin that ships this one along with the rest of its 15 skills.

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 superforge-handoff

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-handoff"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 229 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,584 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00229 $0.01584
Opus 5 $0.00114 $0.00792
Sonnet 5 $0.00046 $0.00317
Haiku 4.5 $0.00023 $0.00158

Measured 9d ago against content hash db0c44ab8c50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

superforge-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 9d 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/superforge-handoff/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Superforge Handoff — Cross-Model Session Transition Protocol

Use this skill whenever switching AI models, before clearing long chat threads, or when ending a work session. It writes a structured handoff capsule to .handoff/ so any AI model can instantly resume work.


1. Triggering Handoff (/handoff or /superforge-handoff)

  1. Ensure directory .handoff/ exists.
  2. Create capsule file: .handoff/YYYY-MM-DD-<slug>.md.
  3. Populate the Resume Capsule (under 80 lines):
    • Project & Passphrase (<repo>: <catchy phrase>)
    • Objective & Verified State
    • Running Processes & Active Ports
    • The docs/ ledger — see below. This is the part that carries the decisions; without it the capsule carries the conversation instead
    • Immediate Next Steps
    • Files to Read First

The docs/ ledger — do not skip this

List every file in docs/, not a summary of them. One row each, read from the file's own header block:

## docs/
| File | Status | Last updated | Open questions |
|---|---|---|---|
| superforge.md | agreed | 2026-07-29 | — (会話=日本語 / ファイル=英語) |
| product-idea.md | agreed | 2026-07-30 | none |
| business-model.md | draft | 2026-07-31 | pricing tier 3 undecided |
| design.md + design.html | agreed | 2026-07-31 | — |
| accessibility.md | draft | 2026-07-29 | 3 criteria not assessed |
| verification.md | — | — | **not run yet** |
| security.md | FINDINGS-OPEN | 2026-07-31 | 1 High 未対応 |
| ship-readiness.md | — | — | **not run yet** |
| failforward.md | 6 entries | 2026-07-31 | 1 mitigation, cause still unknown |

Five rules that make this worth writing:

  • superforge.md goes first, and its language settings travel with it. A resumed session that starts replying in the wrong language has lost something the user set explicitly, and will be corrected manually every time.
  • A file that does not exist gets a row saying so. "verification.md — not run yet" is the single most useful line in the capsule, because it tells the next session what has not been proven. A missing row reads as "handled."
  • Copy the Status and Last updated from each file's own header, not from memory. A capsule that claims agreed for something still marked draft is worse than no capsule.
  • Carry every ## Open questions section forward. Those are exactly the decisions an unattended run is allowed to make with a logged default — losing them means the next session either re-asks or re-decides silently.
  • failforward.md is the one row that is a count, not a status. Note the number of entries and, specifically, any mitigation shipped without a root cause — an open failure the next session would otherwise rediscover the hard way.

Read the full file on GitHub · 142 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 142 lines · 229 tokens per session scan A db0c44ab8c50

Subscribe to this mod's changes

superforge-handoff is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 24d ago), licensed MIT. It adds 229 tokens to every session and 1,584 once invoked, about $0.0011 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.