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 uchicago-dsi/ai-sci-skills --skill handoffgit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-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/uchicago-dsi/ai-sci-skills/handoff)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/handoff"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/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/uchicago-dsi/ai-sci-skills/handoff"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/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 | $0.00046 | $0.00584 |
| Opus 5 | $0.00023 | $0.00292 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00058 |
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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Optimize For Cold Restarts
- A handoff is for a fresh agent with no working memory.
- The goal is fast re-entry, not a narrative recap.
- Update the canonical notebook or log first if the project already has one. Then write the handoff.
- Compose this skill with domain skills such as
$lab-notebook,$job-babysitting, or$slurm.
Use This Contract
Every handoff should answer:
- Goal:
- what problem or decision is in flight.
- Current state:
- what is true now.
- Evidence:
- exact paths, job IDs, branches, commits, configs, logs, or artifacts that support the current read.
- Open uncertainty:
- what is still unclear, blocked, or waiting.
- Next action:
- the exact next check, command, or edit that should happen first.
Make The Handoff Restartable
- Include exact file paths and identifiers, not vague references such as "the latest run" or "that config".
- Separate facts from hypotheses.
- Name what has already been ruled out so the next agent does not repeat dead work.
- If code changed, include branch, commit SHA if any, validation status, and whether the worktree is dirty.
- If jobs are involved, include job IDs, current state, run root, and the next decision point.
- If waiting on an external event, say what event should trigger the next step.
- End with one concrete re-entry action.
Keep It Short
- Default target: 5-12 lines or a very short bullet list.
- Prefer one crisp sentence per field over a long paragraph.
- If the handoff is getting long, move durable detail into the project notebook and keep the handoff as an index into that evidence.
Avoid Weak Handoffs
- Do not retell the whole chronology.
- Do not say "continue from here" without naming the first command or check.
- Do not omit the current best explanation.
- Do not omit validation status after code changes.
- Do not hide uncertainty behind generic phrases such as "needs more debugging".
Restart Test
- A good handoff lets a fresh agent resume within a couple of minutes using only:
- the handoff,
- the repository,
- the referenced notebooks, logs, and artifacts.
- If that would still require rereading the full chat, the handoff is incomplete.
What ships with it
2 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.
- 9d ago First seen · 65 lines · 46 tokens per session scan A f3fae0bad3a0
handoff is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 584 once invoked, about $0.0002 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.