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 commands/datacore-one/datacore/tomorrowgit 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/tomorrow)<a href="https://agentmods.dev/commands/datacore-one/datacore/tomorrow"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/tomorrow.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 | $0.00016 | $0.05971 |
| Opus 5 | $0.00008 | $0.02985 |
| Sonnet 5 | $0.00003 | $0.01194 |
| Haiku 4.5 | $0.00002 | $0.00597 |
Grade A, and why
tomorrow 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 today.
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 — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tomorrow
Command Context
When to Reference DIP-0011
Always reference when:
- Queuing tasks for nightshift execution
- Routing :AI: tagged tasks to nightshift.org
- Reviewing overnight execution pipeline
- Estimating execution time and cost
Key decisions this DIP informs:
- Task movement from next_actions.org → nightshift.org
- Queue optimization (impact/effort/urgency)
- Nightshift server triggering
Quick Reference
| Question | Answer |
|---|---|
| AI queue? | org/nightshift.org |
| When to run? | End of work day |
| Server trigger? | Push triggers server execution |
| What DIPs govern this? | DIP-0011 (Nightshift), DIP-0009 (GTD) |
Agents This Command Invokes
| Agent | Purpose |
|---|---|
session-learning-coordinator |
Pattern extraction |
coach |
Evening REBT reflection (optional) |
Integration Points
- DIP-0011 - Nightshift pipeline
- DIP-0009 - GTD daily end workflow
- /today - Morning counterpart
"End of watch. Securing all stations for the night."
End-of-day command that closes out today, celebrates accomplishments, and builds excitement for tomorrow. The counterpart to /today.
Purpose
- Celebrate what you accomplished today
- Process inbox to zero (or delegate)
- Delegate work to AI for overnight execution
- Ensure system is clean and synced
- Build excitement for tomorrow
Duration
~10 minutes (mostly automated, optional user input)
Behavior
Execute the evening shutdown sequence with a focus on accomplishment and anticipation.
Step 0: Create Tracked Checklist (MANDATORY FIRST STEP)
Before doing anything else, create a tracked task list for the /tomorrow steps. This prevents step skipping in end-of-day processing.
Use TaskCreate to create one task per major step:
Tasks to create (mark in_progress when starting, completed when done):
1. "Sync and inbox status" (activeForm: "Checking sync and inbox")
2. "Quick diagnostics" (activeForm: "Running diagnostics")
3. "Day summary and goal achievement" (activeForm: "Computing daily score")
4. "Journal entry" (activeForm: "Writing journal entry")
5. "Evening coaching" (activeForm: "Running evening check-in")
6. "DIP gap detection" (activeForm: "Scanning for DIP gaps")
7. "Task housekeeping + priorities" (activeForm: "Processing tasks")
8. "AI delegation review" (activeForm: "Reviewing AI task queue")
9. "Tomorrow preview + final status" (activeForm: "Generating preview")
10. "Verify all checklist tasks completed" (activeForm: "Verifying checklist completion")
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.
- today First seen · 770 lines · 16 tokens per session scan A 49d2b679a19c
tomorrow is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 5,971 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-archive
Archive the active PRD (blocked until every accepted finding has a receipt).
prd-map
Build a codebase map so PRDs are written with repo context, not blind.
prd-split
Split the approved PRD into one issue spec per manifest entry.
rca-check
Lint an RCA or premortem document against the canonical template.
prd-os-init
Initialize prd-os in this repo (writes .prd-os/config.json).