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 | $0.00150 | $0.06726 |
| Opus 5.5 | $0.00060 | $0.02690 |
| Sonnet 5.5 | $0.00030 | $0.01345 |
| Haiku 4.5 | $0.00015 | $0.00673 |
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 8d 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 — 345 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.
See references/structured-evidence-format.md for the evidence.json layer and
references/docsgpt-concepts.md for adaptive-depth 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"
When NOT to use
- Entity vetting/dossiers → use
entity-research(has sanctions screening, structured lenses) - Recurring news digests → use
news-monitoring(has cron, dedup, multi-language) - Source-grounded Q&A from collected sources → use
notebooklm-mode(has vault + RAG) - Quick factual question → just use
web_searchdirectly - Single-source extraction → use
web_search+web_extract
Architecture
User question
→ Step 0: Clarification (optional — assess if question is too vague)
→ Step 1: Plan (sub-questions, key topics, success criteria, category, language, complexity)
→ Step 2: Date grounding + language anchor
→ Step 3: Iterative loop (max rounds = complexity cap: simple=2, moderate=3, complex=5)
├─ 3a: Generate gap-driven queries (incl. refute queries from round 2+, empty-search refinement)
├─ 3b: Search (web_search) + fetch (web_extract)
├─ 3c: Quality filter + extraction + source quality classification + numbered citations
├─ 3d: Synthesize into cumulative research state (with token budget check)
├─ 3e: Structured evidence (optional: evidence.json for 5+ sources)
└─ 3f: Stopping check (LLM evaluates coverage + token budget)
→ Step 4: Final report (overview-first structure, see template)
→ Step 5: Stats summary
What ships with it
14 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.
- evals/routing-fixtures.json 5.1 KB
- references/anotiawang-deep-research-concepts.md 7.2 KB
- references/docsgpt-concepts.md 4.4 KB
- references/real-estate-investment-analysis.md 4.8 KB
- references/recursive-research-concepts.md 2.8 KB
- references/skills-monetization.md 6.7 KB
- references/step3-iterative-loop.md 20 KB
- references/structured-evidence-format.md 14 KB
- references/validation-gates.md 13 KB
- scripts/research_validation.py 55 KB runs code
- tests/__init__.py 0 B runs code
- tests/test_gate_hardening_v180.py 14 KB runs code
- tests/test_quote_anchoring_v190.py 8.7 KB runs code
- tests/test_research_validation.py 2.7 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.
- 8d ago Changed · -178 lines fec218ff797d
- 13d ago Changed · +72 lines 900a295192c8
- 20d ago Changed · -9 lines · +3 tokens per session 1203ef12d1b0
- 26d ago Changed · +2 lines f117f1407323
- 1mo ago Changed 5a7a520d6dad
- 1mo ago Changed · -55 lines 1205f21a3dd0
- 1mo 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 (112 stars, last pushed 4d ago), licensed MIT. It adds 150 tokens to every session and 6,726 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
telnyx-voice-advanced-curl
Advanced call control features including DTMF sending, SIPREC recording, noise suppression, client state, and supervisor controls. This skill provides REST API (curl) examples.
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
telnyx-acp-payment
Add credit to a Telnyx account through an Agentic Commerce Protocol (ACP) checkout, paying with a Stripe Link agent wallet or Tempo USDC, then verify the order and balance.
telnyx-verify-curl
Look up phone number information (carrier, type, caller name) and verify users via SMS/voice OTP. Use for phone verification and data enrichment. This skill provides REST API (curl) examples.
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.
telnyx-import-elevenlabs
Import ElevenLabs conversational AI agents into Telnyx. Preserves instructions, voice settings, tools, and call analysis. Supports all SDK languages.