Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/datacore-one/datacorenpx agentmods add commands/datacore-one/datacore/wrap-upWrote 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/wrap-up)<a href="https://agentmods.dev/commands/datacore-one/datacore/wrap-up"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/wrap-up/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/wrap-up"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/wrap-up.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 | $0.00012 | $0.20728 |
| Opus 5.5 | $0.00005 | $0.08291 |
| Sonnet 5.5 | $0.00002 | $0.04146 |
| Haiku 4.5 | $0.00001 | $0.02073 |
Grade B, and why
wrap-up scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
generated and `chmod 444` the moment a space flips to Phase 1, and the projector's How it starts
The opening of the file, as written. The whole thing — 1,591 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Wrap-Up
EXECUTION MODEL — INLINE WITH TRACKED CHECKLIST
Execute /wrap-up inline in the main conversation. The tracked checklist (Step 0b) prevents
step-skipping by making every step visible as an unticked line in today's journal, written and
ticked by the Datacore step tracker (command_steps.py), the same in every harness.
Why not subagent: Subagent dispatch (tried 2026-04-11) produces zero console output for 15-20 minutes — unacceptable UX. The user sees nothing while the agent runs 170+ tool calls in the background. The tracked checklist is the actual compression guard, not process isolation.
Anti-compression rule: If you feel tempted to skip steps 6-9 ("no tasks to extract", "nothing to verify"), STOP. The checklist forces you to tick each step as it completes. You cannot skip what is tracked. This is the fix for ENG-2026-0411-001.
Command Context
When to Reference DIP-0016
Always reference when:
- Capturing session learnings
- Creating continuation tasks
- Updating journals across spaces
- Syncing context and repos
Key decisions this DIP informs:
- Session memory extraction
- Bootstrap prompt format for continuations
- Per-space journal routing
Quick Reference
| Question | Answer |
|---|---|
| When to run? | Before closing terminal |
| Duration? | ~2-5 minutes |
| Key output? | Continuation tasks, journal entries, patterns |
| What DIPs govern this? | DIP-0016 (Session Memory), DIP-0009 (GTD) |
Agents This Command Invokes
| Agent | Purpose |
|---|---|
journal-coordinator |
Per-space journal entries |
context-maintainer |
Context sync, only if preflight reports registry changes |
coach |
Quick emotional check (optional) |
No longer invoked here: session-learning-coordinator, session-learning, learning-classifier. Learning moved to the nightly batch sweep — see §5. Spawning any of them from this command re-creates the cost this revision removed.
Scripts This Command Calls
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 Changed 209cc5e26226
- 10d ago Changed · +15 lines e8abd574c526
- 18d ago Changed · +25 lines b95dcb3ffd63
- 20d ago Changed · +11 lines d2696e749320
- 22d ago Changed · +49 lines dcd5723a3531
- 1mo ago Changed · +32 lines d0439bf89ae3
- 1mo ago Changed · +1 lines 48e11653df7e
- 1mo ago First seen · 1,458 lines · 12 tokens per session scan B 167cb85a0d01
wrap-up is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 20,728 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.
loops
Weekly review — surface everything in-flight and force a ship / block / kill decision on each.
open
Open the memex vault in Finder or Obsidian.
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.
para-status
Show an overview of your PARA system — item counts, statuses, and attention-needed flags.
dejavu-resume
Find the best matching past Claude Code session and produce a ready-to-run resume command.