dual-tool-handoff

dual-tool-handoff is a skill for Claude Code, Codex from freezingfunky/ashwin-skills. It costs 76 tokens per session (2,600 once invoked), scanned A, original, MIT.

A file-based handoff workflow for moving a named task between Cursor and Claude Code. It records the current state in .scratch/handoffs/ because chat history does not automatically transfer between tools.

In plain words
What is it for?
Use it when switching tools, resuming a named thread, or fetching a handoff from the other tool's local session store.
Why use it?
It gives the next coding tool a written summary of what was completed and what remains, with checks for differences between the handoff and the working tree.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it when switching tools, resuming a named thread, or fetching a handoff from the other tool's local session store.

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

Made for: Claude Code, Codex.

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 dual-tool-handoff

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/freezingfunky/ashwin-skills/dual-tool-handoff"><img src="https://agentmods.dev/badge/skills/freezingfunky/ashwin-skills/dual-tool-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,600 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 $0.00076 $0.02600
Opus 5 $0.00038 $0.01300
Sonnet 5 $0.00015 $0.00520
Haiku 4.5 $0.00008 $0.00260

Measured 11d ago against content hash 8fcb18d043df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dual-tool-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 11d 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/dual-tool-handoff/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dual-tool handoff — opt-in, named, switch-only

Chats do not sync across Cursor, Claude Code, Codex, etc. The repo file does. Off by default — only act when the user asks for a handoff / resume / fetch.

Diff ≠ why. Git supplies paths; the agent curates shipped / left. Diff check warns when they look misaligned — it never rewrites the story and never blocks the write.

Contract

  • Named: every handoff gets a short thread-summary name (e.g. auth-form-ui, oss-skills-launch) — same string both tools use to resume.
  • Always ask which thread before write or resume (unless the user already named one in the same message).
  • Switch-only: use this when leaving one tool for the other. It does not keep two live sessions in sync. Last write to LATEST.md is “what I’m switching to now.”
  • Not parallel sync: if two chats write at once, they will clobber LATEST; prefer one active switch at a time. Older named files remain for explicit resume.
  • Diff check: script fills Tree + Paths; agent fills Alignment + Note. warn ≠ block.
  • Fetch / hydrate: if the handoff file is missing (or the user force-refreshes), resolve a session from the other tool’s local store → confirm → summarize into the handoff schema. Titles move; session ids are the join key.

When not to use

  • The user did not ask to hand off / resume / fetch.
  • Same-tool session compact (use that product’s native handoff).
  • Trying to mirror two tools running at the same time — out of scope; pick one writer, then switch.
  • Live cross-platform text pings, batch migrate, or Codex store adapters — out of scope.
  • Writing into Claude/Cursor session databases — read-only resolve only.

Cursor store caveat

Cursor’s on-disk format is undocumented and can change; WAL may require a DB copy while Cursor is open. If session-resolve --from cursor fails, fall back to a manual handoff write. File-first still works.

Pick the thread (do this first)

Read the full file on GitHub · 214 lines

Files

What ships with it

4 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. 11d ago First seen · 214 lines · 76 tokens per session scan A 8fcb18d043df

Subscribe to this mod's changes

dual-tool-handoff is a skill published in the GitHub repository freezingfunky/ashwin-skills (2 stars, last pushed 24d ago), licensed MIT. It adds 76 tokens to every session and 2,600 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.