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.
git clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/commands/datacore-one/datacore/handover)<a href="https://agentmods.dev/commands/datacore-one/datacore/handover"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/handover/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/commands/datacore-one/datacore/handover"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/handover.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 | $0.00033 | $0.00835 |
| Opus 5.5 | $0.00013 | $0.00334 |
| Sonnet 5.5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
handover 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handover
Use when a session on the Mac has grown into work the Mac cannot carry —
evals, promise runs, several agents in parallel. The same conversation, with
its full history, continues on dayshift in tmux; the owner reattaches with
ds <name> from any machine. Files the dayshift session shows the owner
(mac-open) open on the Mac.
This is not /continue --save, which leaves a written summary for later.
Here the conversation itself moves, now.
Spec: 2-datacore/1-tracks/dev/superpowers/specs/2026-10-28-handover-design.md
The two halves, and why
You (the agent) wind the session down and write the checkpoint. The owner
copies the transcript: the permission check refuses an agent copying its own
transcript, and that refusal is not to be routed around — no osascript,
no new terminal window, no subprocess that does it for you.
Steps
-
Stop in-flight work. List every background shell and subagent you started that is still running. Stop each one. For each, write down what it was doing, how far it got (files written, last result seen), and the exact prompt or command that restarts it. Save the list as JSON in the scratchpad:
[{"what": "...", "progress": "...", "relaunch": "..."}]([]when nothing was running). -
Name the permission mode you are in, as the system reminders state it (for example
auto). Omit it only when no mode is stated. The resumed session gets the same mode and the Mac session's launch flags — never wider. -
Record every file this session wrote, including files written through Bash, which the transcript does not count:
python3 ~/Data/.datacore/lib/wrap_up_mechanics.py files --add <path>... -
Checkpoint:
python3 ~/Data/.datacore/lib/handover.py checkpoint --topic "<3-6 words>" --mode <mode> --inflight <json file>It commits and pushes the session's files with
/wrap-up's rules (session files only, default branch only, others' changes reported and left alone). If it printshandover stopped:, show the owner each line in plain words and stop here — something would be missing on dayshift. Code repos under2-projects/are never committed by it: commit and push those (or open the PR) first, then rerun.
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.
- yesterday First seen · 77 lines · 33 tokens per session scan A 9af5618f6b22
handover is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 835 once invoked, about $0.0001 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 2026-10-29.
Other commands, from other repositories
open
Open the memex vault in Finder or Obsidian.
sync
Manually sync current session to GitHub now.
telegram-secretary
A command entry point for registering, configuring, and managing a Telegram secretary that runs continuously on Anthropic’s cloud routines. Its specification is kept in a referenced skill file and routine prompt.
worktree-cleanup
A command for removing a Git worktree, which is a separate working folder linked to the same repository, after its pull request is merged.
iteration-loop
Run a whole iteration Phase 1→6 autonomously — code-first direction lock with a retained prototype, then execute → close → PR → merge-ready → post-merge close. Optional direction hint and scale S|M|L|XL; explicit autonomous opt-in, no grill-me, no routine confirmation.
setup
Configure mnemonic for proactive memory operations.