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 moonlight-lupin/agent-skills --skill deep-researchgit clone --depth 1 https://github.com/moonlight-lupin/agent-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/moonlight-lupin/agent-skills/deep-research)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/deep-research"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/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/moonlight-lupin/agent-skills/deep-research"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.08037 |
| Opus 5 | $0.00073 | $0.04019 |
| Sonnet 5 | $0.00029 | $0.01607 |
| Haiku 4.5 | $0.00015 | $0.00804 |
Grade A, and why
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research — Iterative Research Engine
An autonomous, multi-step research engine that performs exhaustive information
gathering and synthesis. Unlike a single web_search, this skill implements an
iterative loop where the agent plans, searches, extracts, synthesizes, and
decides when to stop — producing a cited report with structured evidence,
source quality tiers, and explicit gaps/contradictions sections.
Inspired by PewDiePie's Odysseus project, Alibaba/Tongyi's IterResearch
approach, and the sn-deep-research evidence-structuring architecture
(OpenSenseNova/SenseNova-Skills, MIT). The full 9-role sn pipeline was
evaluated and intentionally NOT adopted — only the evidence.json layer and
refute-polarity requirement were ported, based on empirical side-by-side
testing (July 2026). See references/structured-evidence-format.md.
v1.2.0 changes (July 2026): overview-first report structure (comparison table right after executive summary), language anchoring (BCP 47), structured evidence step (3e), refute polarity requirement, source quality classification, explicit contradictions + gaps sections. Architecture diagram corrected.
v1.3.0 changes (July 2026): source quality ranking and weighting — primary (3×) > secondary (2×) > tertiary (1×). Conflict resolution by quality tier. Quality distribution check (healthy/acceptable/weak) before writing. Tertiary source overreliance pitfall. Source table now shows quality distribution summary. Prompted by user noting too many tertiary sources in the self-hosting vs API report.
v1.5.0 changes (July 2026): adaptive depth (complexity-based round caps),
optional clarification phase (Step 0), token budget awareness, numbered
citations, progressive empty-search refinement, explicit synthesis prompt
structure. Concepts adapted from DocsGPT's ResearchAgent (arc53/DocsGPT, MIT).
See references/docsgpt-concepts.md for the concept mapping.
When to use
- User asks for "deep research", "research report", "comprehensive analysis"
- User wants a written report on a topic (not just a quick answer)
- Question requires multi-source synthesis with citations
- User says "look into X in depth" or "write a report on X"
What ships with it
5 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.
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.
- 10d ago First seen · 513 lines · 147 tokens per session scan A 6e695dbbca63
deep-research is a skill published in the GitHub repository moonlight-lupin/agent-skills (60 stars, last pushed 3d ago), licensed MIT. It adds 147 tokens to every session and 8,037 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.