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/nightshift-hookgit 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/nightshift-hook)<a href="https://agentmods.dev/commands/datacore-one/datacore/nightshift-hook"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/nightshift-hook.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 | $0.00008 | $0.01243 |
| Opus 5 | $0.00004 | $0.00622 |
| Sonnet 5 | $0.00002 | $0.00249 |
| Haiku 4.5 | $0.00001 | $0.00124 |
Grade A, and why
nightshift-hook 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Hook: Nightshift Integration
Command Context
When to Reference Research Module
Always reference when:
- Nightshift overnight pipeline is executing
- Research queue has pending TODO items in research_learning.org
- Need to process links and generate podcasts before morning briefing
Key decisions this hook informs:
- How many items to process this cycle (respects max_sources_per_night)
- Whether to generate podcasts (checks nlm availability)
- Which focus areas have the most pending items
Quick Reference
| Question | Answer |
|---|---|
| When does this run? | Nightshift research timer (02:00 UTC) |
| What does it process? | TODO items from research_learning.org |
| Does it generate podcasts? | Yes, if nlm CLI is available and >= 3 sources processed |
| What's the processing limit? | max_sources_per_night setting (default 20) |
| What outputs are created? | Literature notes, zettels, podcasts, journal entry, action items |
Agents This Hook Invokes
| Agent | Purpose |
|---|---|
| research-orchestrator | Full pipeline: discovery, extraction, synthesis, podcasts, post-processing |
Integration Points
- research_learning.org - Source of TODO items to process
- research-orchestrator agent - Invoked in nightshift mode (non-interactive)
- podcast-creator agent - Spawned by orchestrator for podcast generation
- 0-personal/content/podcasts/ - Podcast output directory
- Journal - Session summary written to daily journal
This hook is invoked by nightshift for overnight research processing.
Trigger
Called by nightshift scheduler via nightshift run --command=/research-daily.
Mode
Non-interactive. No user confirmation needed — process all eligible TODO items.
Workflow
Step 1: Count and Prioritize Research Queue
Read research_learning.org and count pending items:
import sys
from pathlib import Path
sys.path.insert(0, '.datacore/modules/research/lib')
data_root = Path.home() / "Data"
research_org = data_root / "0-personal" / "org" / "research_learning.org"
# Count TODO items
todo_count = 0
if research_org.exists():
content = research_org.read_text()
todo_count = content.count("** TODO") + content.count("*** TODO")
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 · 190 lines · 8 tokens per session scan A 0219bece550b
nightshift-hook is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,243 once invoked, about $0.0000 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).