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.
npx skills add freezingfunky/ashwin-skills --skill dual-tool-handoffgit clone --depth 1 https://github.com/freezingfunky/ashwin-skillsWrote 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.
[](https://agentmods.dev/skills/freezingfunky/ashwin-skills/dual-tool-handoff)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mdis “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)
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.
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.
- 11d ago First seen · 214 lines · 76 tokens per session scan A 8fcb18d043df
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.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.