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/continuegit 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/continue)<a href="https://agentmods.dev/commands/datacore-one/datacore/continue"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/continue.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 | $0.05275 |
| Opus 5 | $0.00008 | $0.02638 |
| Sonnet 5 | $0.00003 | $0.01055 |
| Haiku 4.5 | $0.00002 | $0.00528 |
Grade A, and why
continue 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 — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue
Command Context
When to Reference DIP-0016
Always reference when:
- Resuming incomplete work from previous sessions
- Finding high-impact next actions
- Loading bootstrap context from continuation tasks
- Suggesting work based on system state
Key decisions this DIP informs:
- Bootstrap prompt retrieval from :continuation: tasks
- Session memory queries for context
- Task prioritization (impact vs effort)
Quick Reference
| Question | Answer |
|---|---|
| When to run? | Start of session, or when looking for what to work on |
| Duration? | ~1-2 minutes |
| Key output? | Loaded context, suggested next action |
| What DIPs govern this? | DIP-0016 (Session Memory), DIP-0009 (GTD) |
Agents This Command Invokes
Integration Points
- DIP-0016 - Session memory retrieval
- DIP-0009 - Task scanning and prioritization
- /wrap-up - Creates continuation tasks this command consumes
- /today - Morning complement (broader scope)
Resume incomplete work or find the highest-impact next action.
CRITICAL: Task Access Pattern
ALWAYS use org-workspace for task operations. NEVER grep raw org files.
The GTD module's 11 MCP tools (listed in module.yaml) are NOT registered on any MCP server — they are phantom tools. Until they are wired into the datacore MCP server, access tasks via:
-
Python inline (preferred for structured queries):
python3 -c " from org_workspace import OrgWorkspace, Query ws = OrgWorkspace() ws.load('/path/to/org/inbox.org') q = Query(ws) tasks = q.by_tag('continuation') # or by_state, agenda, deadlines, etc. for t in tasks: print(f'[{t.todo}] {t.heading} scheduled={t.scheduled}') " -
CLI adapter (for specific operations):
python3 .datacore/lib/org_workspace_adapter.py list --file [path] --tags continuation --states TODO python3 .datacore/lib/org_workspace_adapter.py agenda --file [path] --days 7 python3 .datacore/lib/org_workspace_adapter.py ensure-ids --file [path]
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 · 650 lines · 16 tokens per session scan A d397bc61337e
continue 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 5,275 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.
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).
prd-approve
Advance the active PRD to approved (blocked by pending findings).