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 Agents365-ai/365-skills --skill scholar-deep-researchgit clone --depth 1 https://github.com/Agents365-ai/365-skillsWrote 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/agents365-ai/365-skills/scholar-deep-research)<a href="https://agentmods.dev/skills/agents365-ai/365-skills/scholar-deep-research"><img src="https://agentmods.dev/badge/skills/agents365-ai/365-skills/scholar-deep-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/agents365-ai/365-skills/scholar-deep-research"><img src="https://agentmods.dev/badge/skills/agents365-ai/365-skills/scholar-deep-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 | $0.00000 | $0.08529 |
| Opus 5 | $0.00000 | $0.04265 |
| Sonnet 5 | $0.00000 | $0.01706 |
| Haiku 4.5 | $0.00000 | $0.00853 |
Grade A, and why
scholar-deep-research 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- assets/prompts/self_critique.md 5.0 KB
- assets/templates/comparative_analysis.md 2.1 KB
- assets/templates/grant_background.md 1.9 KB
- assets/templates/literature_review.md 2.1 KB
- assets/templates/scoping_review.md 2.1 KB
- assets/templates/systematic_review.md 2.7 KB
- changelog.d/README.md 1.9 KB
- CHANGELOG.md 11 KB
- references/agent_prompts/phase3_deep_read.md 9.7 KB
- references/cli_contract.md 3.2 KB
- references/env_vars.md 5.0 KB
- references/example_run.md 3.0 KB
- references/pitfalls.md 6.3 KB
- references/quality_assessment.md 4.8 KB
- references/report_templates.md 4.0 KB
- references/search_strategies.md 4.3 KB
- references/source_selection.md 3.1 KB
- references/state_schema.md 2.8 KB
- requirements.txt 310 B
- scripts/__pycache__/_common.cpython-311.pyc 44 KB
- scripts/__pycache__/_locking.cpython-311.pyc 7.4 KB
- scripts/__pycache__/_pdf_fetch.cpython-311.pyc 14 KB
- scripts/__pycache__/state_apply.cpython-311.pyc 23 KB
- scripts/_common.py 36 KB runs code
- scripts/_gates.py 19 KB runs code
- scripts/_locking.py 5.0 KB runs code
- scripts/_pdf_fetch.py 12 KB runs code
- scripts/_s2_citations.py 6.9 KB runs code
- scripts/_search_meta.py 5.2 KB runs code
- scripts/build_citation_graph.py 19 KB runs code
- scripts/dedupe_papers.py 12 KB runs code
- scripts/export_bibtex.py 7.0 KB runs code
- scripts/extract_pdf.py 19 KB runs code
- scripts/list_sources.py 5.0 KB runs code
- scripts/prefetch_pdfs.py 14 KB runs code
- scripts/rank_papers.py 11 KB runs code
- scripts/render_report.py 18 KB runs code
- scripts/research_state.py 60 KB runs code
- scripts/resolve_id.py 5.8 KB runs code
- scripts/search_arxiv.py 6.2 KB runs code
- scripts/search_biorxiv.py 7.5 KB runs code
- scripts/search_crossref.py 5.3 KB runs code
- scripts/search_dblp.py 6.1 KB runs code
- scripts/search_exa.py 12 KB runs code
- scripts/search_openalex.py 6.8 KB runs code
- scripts/search_pubmed.py 6.7 KB runs code
- scripts/skim_papers.py 9.9 KB runs code
- scripts/state_apply.py 18 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/_helpers.py 3.2 KB runs code
- scripts/tests/run.py 1.1 KB runs code
- scripts/tests/test_agent_native.py 10 KB runs code
- scripts/tests/test_citation_chase_filter.py 3.8 KB runs code
- scripts/tests/test_citation_chase_s2.py 10 KB runs code
- scripts/tests/test_dedupe_bridge.py 9.7 KB runs code
- scripts/tests/test_envelope.py 1.9 KB runs code
- scripts/tests/test_evidence_from_json.py 10 KB runs code
- scripts/tests/test_export_formats.py 2.3 KB runs code
- scripts/tests/test_extract_pdf_engine.py 7.6 KB runs code
- scripts/tests/test_g4_topic_mismatch.py 4.4 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.
- 12d ago First seen · 420 lines · 0 tokens per session scan A ed72b3869e19
scholar-deep-research is a skill published in the GitHub repository Agents365-ai/365-skills (48 stars, last pushed yesterday), with no licence file. It costs nothing until one of its globs matches a file; then it loads 8,529 tokens. 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 2026-08-30.
Other skills, from other repositories
drawio-skill
Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams. Use when the user explicitly requests draw.io/diagrams.net, needs a polished architecture, ERD, UML, sequence, C4, SysML, BPMN, network, swimlane, ML, or infrastructure diagram, wants code/IaC/SQL/OpenAPI/AsyncAPI/Protobuf converted into…
cocosketch
Generate visual draw.io diagrams from CocoPlus artifacts via a deterministic seven-step pipeline.
bruce-drawio
Use this skill when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram. Trigger words: "draw", "diagram", "flowchart", "architecture", "UML", "sequence diagram", "mindmap", "ER diagram", "network topology", "visualize", "draw.io"…
FlowForge
A draw.io diagram tool that turns a description or document into editable visual diagrams. Draw.io is software for making flowcharts, system diagrams, and other structured illustrations.
atet
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
query-kb
Load scoped repository context, then search and navigate a hraness/kb Markdown vault with hybrid text retrieval, exact metadata, bounded links and typed relationships, backlinks, whole-vault graph reports, and optional Git provenance. Use when an agent needs the applicable repository instructions, rationale, prior…