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 agentmods add skills/hmbown/codewhale/handoffnpx skills add Hmbown/CodeWhale --skill handoffgit clone --depth 1 https://github.com/Hmbown/CodeWhaleWrote 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/hmbown/codewhale/handoff)<a href="https://agentmods.dev/skills/hmbown/codewhale/handoff"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/handoff.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01216 |
| Opus 5 | $0.00035 | $0.00608 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint. The goal: the durable artifact survives, the context does not need to.
Invocation: model+user
When to use
- The user says "handoff", "hand off", "pass the baton", "takeover prompt", "write me a handoff", or the session is about to end / compact.
- A long operation (multi-turn, multi-workstream) has state that must survive context loss: commits, branches, PRs, CI, blockers, decisions.
- You are switching to a fresh session and want the new session to start from evidence instead of reconstructing the old one.
What to do
-
Gather the truth from tools, not memory. Run/collect:
git branch --show-current,git status --short,git log --oneline origin/<default>..HEAD(what is local-only),git log --oneline -5(recent context).- Live remote state where relevant (
gh pr list --state open,gh pr checks <n>,gh run list) — only what the user's operation actually depends on; do not pad the handoff with a full GitHub dump. - Any in-flight work: dirty files, uncommitted slices, partial worktrees, running background jobs/workers, queued CI.
-
Write a compact markdown handoff (aim under ~60 lines; the user may also ask for a "short text-only" variant — then aim under ~15 lines):
# Handoff — <operation/session name> — <date> - **State:** <one-line: what is done vs in-flight vs blocked> - **Landed/committed:** <exact SHAs + one-line what> - **Branches/PRs:** <names + states; which are ours vs community> - **CI:** <what is green, what is waiting, what is broken> - **Blockers:** <exact blocker + what would unblock> - **Decisions made:** <the WHY that a fresh session must not re-litigate> - **Next step:** <the single next action, one line> - **Continuation records:** <pointers to partial work that must be preserved (worktrees, uncommitted files, receipts)>
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.
- 4d ago First seen · 98 lines · 70 tokens per session scan A 8f809e2e32a7
handoff is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,216 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 2026-08-30.
Other skills, from other repositories
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
ultraapp-interview
Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
visual-acceptance
UI/视觉改动交付前的终验方法论——多主题截图矩阵复现、像素真值判据链、CSS 层叠陷阱、布局漂移审查、before/after 存证。当视觉改动需要验收（而非实现）时使用：交付前最后一环，回答「看得见的部分真的对吗」。.