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 skills add datacore-one/datacore --skill researchgit 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/skills/datacore-one/datacore/research)<a href="https://agentmods.dev/skills/datacore-one/datacore/research"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/research/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/skills/datacore-one/datacore/research"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/research.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 | $0.00019 | $0.00328 |
| Opus 5.5 | $0.00008 | $0.00131 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
Research for Datacore 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 1mo ago.
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.
What it actually says
Research for Datacore
Automated research processing — curate links, generate NotebookLM podcasts, extract knowledge artifacts, and build industry landscapes.
Tagline: "Curate links. Wake up to podcasts and insights."
What This Module Provides
Tools (MCP):
datacore.research.queue— List pending research links and processing statusdatacore.research.sources— Manage and query research source registry
Skills:
- Research status checking
- Ad-hoc podcast creation
Agents:
research-orchestrator— Full pipeline orchestration (DIP-0021)podcast-creator— NotebookLM podcast generation
Commands:
/research-daily— Manually trigger daily research processing
When to Use
Triggers: research, podcast, readwise, sources, literature, zettel, notebooklm.
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 262 B
- agents/podcast-creator.md 1.1 KB
- agents/research-orchestrator.md 2.1 KB
- CLAUDE.base.md 8.8 KB
- commands/create-podcast.md 7.1 KB
- commands/nightshift-hook.md 5.8 KB
- commands/research-daily.md 6.0 KB
- commands/research-status.md 12 KB
- commands/today-hook.md 4.6 KB
- docs/pipeline-podcasts.md 5.9 KB
- lib/__init__.py 26 B runs code
- lib/adapters/__init__.py 96 B runs code
- lib/adapters/readwise.py 8.1 KB runs code
- lib/migrate_research_props.py 8.2 KB runs code
- lib/nlm_auth_sync.py 10 KB runs code
- lib/research_orchestrator.py 77 KB runs code
- lib/research_router.py 14 KB runs code
- lib/sync_state.py 2.8 KB runs code
- lib/tests/__init__.py 0 B runs code
- lib/tests/test_audio_availability_state.py 2.3 KB runs code
- lib/tests/test_audio_failure_reason.py 1.9 KB runs code
- lib/tests/test_decisions_research.py 6.0 KB runs code
- lib/tests/test_nlm_auth_deferral.py 1.5 KB runs code
- lib/tests/test_queue_drain.py 8.6 KB runs code
- lib/tests/test_research_formal.py 8.7 KB runs code
- module.yaml 3.9 KB
- README.md 3.9 KB
- requirements.txt 1.5 KB
- skills/create-podcast/SKILL.md 416 B
- skills/research-status/SKILL.md 716 B
- tests/_research_harness.py 4.1 KB runs code
- tests/test_promise_KNW2_queue_to_notes.py 4.2 KB runs code
- tests/test_promise_KNW3_failure_kept_and_told.py 2.9 KB runs code
- tests/test_promise_KNW4_queue_drains_60d.py 3.6 KB runs code
- tests/test_promise_KNW5_podcast_made_saved_reported.py 6.1 KB runs code
- tests/test_promise_MEM_50_failed_page_never_becomes_note.py 4.6 KB runs code
- tools/index.js 5.5 KB runs code
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.
- 1mo ago First seen · 47 lines · 19 tokens per session scan A d448f9a6b72b
Research for Datacore is a skill published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 328 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 2026-09-03.
Other skills, from other repositories
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…
quiz-me
Use right after writing or editing code or files for the user — before ending your turn — to quiz them on what was just built and confirm they actually understand it. Also triggers on "quiz me", "test my understanding", "check what I learned", "comprehension check", or recovering the understanding that vaporizes when…
learn-this
Teach the user a topic and persist what they learn as queryable vault memory, grounded in NotebookLM. Vault-native companion to /teach.
Datacore DIPs
Comprehensive knowledge from all 20 Datacore Improvement Proposals — architecture, patterns, GTD, modules.
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
teach
Teach the user a new skill or concept, within this workspace.