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 AndrewDongminYoo/cc-agents-kit --skill handoffgit clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kitWrote 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/andrewdongminyoo/cc-agents-kit/handoff)<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/handoff"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/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/andrewdongminyoo/cc-agents-kit/handoff"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/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 | $0.00063 | $0.02335 |
| Opus 5.5 | $0.00025 | $0.00934 |
| Sonnet 5.5 | $0.00013 | $0.00467 |
| Haiku 4.5 | $0.00006 | $0.00233 |
Grade A, and why
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 5d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Overview
Produce a detailed, self-contained context summary that lets work continue in a brand-new session with no access to this one. By default, print the output to chat for the user to copy and paste. Use File Mode (below) only when a context-threshold nudge requests it or the user explicitly asks for a handoff file.
When to Use
- The current context is long and answer quality is degrading.
- You want to start fresh while preserving essential context.
- The context window is approaching capacity.
- You need to carry context to another machine, tool, or teammate.
Not this skill: a short durable fact for future sessions → write a memory file in the persistent memory directory and index it in MEMORY.md (auto-loaded each session). Never write memory files from handoff — the two channels serve different lifetimes.
Handoff-first policy: if you run a PreCompact hook that intercepts the first auto-compact of a session (this plugin's own PreCompact hook does not intercept; it only shapes the compaction summary to the template below), its interception message makes this skill the first option: print the handoff immediately and tell the user to /clear and paste it into the fresh session. Only if the user chooses to keep the session does the next auto-compact proceed normally.
If the session has no meaningful work to preserve, say so and stop.
The Gate — should this be a handoff at all?
Ordered tree, run before producing anything; first yes wins.
Every move except Continue trades the session — a primary source — for a summary of it, so rule out the cheap options first.
(Adapted from mattpocock/skills PHASE-BOUNDARIES.md; /compact drops out as a rung here because compaction is automated and its pressure is visible in the statusline.)
- Can the session just continue? The next phase needs this phase's reasoning verbatim, or there is comfortable context left. Continue costs nothing and loses nothing.
- Is the context irrelevant to what comes next? Then recommend
/clearand stop — nothing worth carrying, and the old session stays resumable. Clearing a relevant context is the one-way mistake: the why behind the work doesn't come back from reading the diff. - Is the remaining work a tightly-scoped AFK task? Send it to a subagent and leave this session untouched — no handoff needed.
- Is something actually travelling? A handoff earns its lossiness only when context must cross a boundary: a new harness or tool, a new machine or directory, a teammate, or a side task forked mid-phase. That list is the whole clause.
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.
- 5d ago Changed · +20 lines 4727ec2dbfe7
- 26d ago Changed · +11 lines 27880c83cb85
- 2mo ago First seen · 141 lines · 63 tokens per session scan A 410a88bf30d9
handoff is a skill published in the GitHub repository AndrewDongminYoo/cc-agents-kit (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 2,335 once invoked, about $0.0003 per session on Opus 5.5. 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.
handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| handoffAndrewDongminYoo/cc-agents-kit | Skill | 3 | yesterday | Apache-2.0 | A | 63 | Claude Code |
| resumeArcticFox2029/chamnan | Skill | 10 | 9d ago | MIT | A | 36 | Claude Code |
| handoff-moreSting25/claude-code-handoff | Skill | 5 | yesterday | MIT | A | 110 | Claude Code |
| audit-contextMalo-T/claude-toolbelt | Skill | 2 | yesterday | MIT | A | 218 | Claude Code |
| handoffMalo-T/claude-toolbelt | Skill | 2 | yesterday | MIT | A | 151 | Claude Code |
| handoffSting25/claude-code-handoff | Skill | 5 | yesterday | MIT | B | 106 | Claude Code |
| captureArcticFox2029/chamnan | Skill | 10 | 9d ago | MIT | C | 46 | Claude Code |