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 SerenecoTech/agent-skills --skill handoff-resumegit clone --depth 1 https://github.com/SerenecoTech/agent-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/serenecotech/agent-skills/handoff-resume)<a href="https://agentmods.dev/skills/serenecotech/agent-skills/handoff-resume"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/handoff-resume/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/serenecotech/agent-skills/handoff-resume"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/handoff-resume.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 | $0.00054 | $0.01136 |
| Opus 5 | $0.00027 | $0.00568 |
| Sonnet 5 | $0.00011 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
handoff-resume 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Resume
Pick up in-flight work from a HANDOFF.md so the user never re-explains the task. Locate the handoff, rehydrate the original context, confirm the world hasn't moved, then act on the handoff's declared posture: start the work, confirm once, or ask the blocking questions. Pairs with the handoff skill, which writes the ▶ Resume This Work block this skill reads.
When to Use
- Fresh session and the user says "resume", "continue", "pick up the handoff", "where were we"
- A
HANDOFF.mdis present and the task is unfinished - Switching agents or sessions mid-task
Do NOT use for: a brand-new task, or when the user's message is itself a specific instruction (follow that instead). If no handoff exists, say so; don't invent one.
Process
- Locate the handoff. Explicit path arg if given, else
HANDOFF.mdin cwd, else newest under.claude/handoff/(if several, list them and ask which), else report "no handoff found" and stop. - Read it fully. Find the ▶ Resume This Work block (Posture + Next action). No block? See the legacy row in the posture table.
- Drift check, before acting. Run
git statusandgit log --oneline -10. Compare against the handoff's Branch and any commit it cites. If the tree moved (new commits, different branch, unexpected uncommitted work, or you aren't even in the handoff's working dir), surface it and reconcile before building on the handoff. The handoff is a map written in the past; confirm the territory. - Rehydrate context (do not skip: this is what removes the need to re-explain):
- Built-in agent memory: read each
[[memory-slug]]the handoff links; verify it still exists. Skip if your harness has no file-based memory. - memsearch (optional; only if the handoff has a Memory Recall section and
.memsearch/exists): invoke thememsearch:memory-recallskill (or runmemsearch search "<query>") on the handoff's seed queries plus the goal. Do not read.memsearch/memory/*.mdas files; they are large and built for semantic retrieval. If memsearch isn't installed, skip this and rely on the handoff's own narrative. - Project docs: open the handoff's linked Project Context Docs.
- Built-in agent memory: read each
- Honor the posture (table below). For work that proceeds, build a TodoWrite from Not Yet Done, then start.
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.
- 10d ago First seen · 56 lines · 54 tokens per session scan A 7e072f6bbab0
handoff-resume is a skill published in the GitHub repository SerenecoTech/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 1,136 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…