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 | $0.01635 |
| Opus 5 | $0.00032 | $0.00817 |
| Sonnet 5 | $0.00013 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
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 8d 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 — 141 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. The output is printed to the chat for the user to copy and paste — it is NOT written to a 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). handoff only prints to chat; never write memory files from here — the two channels serve different lifetimes.
Handoff-first policy: the first auto-compact of every session is intercepted by the handoff-first-precompact PreCompact hook. When that interception message appears, this skill IS 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.
- 8d 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 (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,635 once invoked, about $0.0003 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
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
memory-curator
Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…
session-handoff
A human-invoked utility that writes a grounded session-handoff document (plus a continuation pointer memory) so a fresh agent can resume in-progress work. Not auto-invoked; a human runs it deliberately.
furl
How the Furl context-compression plugin works in Claude Code and Codex — the furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist MCP tools, the > retrieval flow, and Claude Code's optional automatic hooks. Use when the user asks what Furl is doing, how to compress or retrieve content, why…