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 Orkas-AI/Orkas-Awesome-AgentSkills --skill deep-researchgit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/deep-research)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/deep-research"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/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/orkas-ai/orkas-awesome-agentskills/deep-research"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/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 | $0.00003 | $0.01820 |
| Opus 5.5 | $0.00001 | $0.00728 |
| Sonnet 5.5 | $0.00001 | $0.00364 |
| Haiku 4.5 | $0.00000 | $0.00182 |
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 2mo 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deep-research
Guide-type skill for rigorous, transparent research. Use it to investigate a complex topic, collect and evaluate evidence, resolve contradictions when possible, and produce a cited research report.
This skill is not a tutoring skill. It does not teach step by step, grade homework, organize local files, or manage a thesis project. It focuses on evidence collection, source evaluation, synthesis, and research reporting.
When to use
Use this skill when the user asks for:
- Deep research, systematic investigation, literature review, competitive research, market/industry research, or trend analysis.
- A report with citations, source-quality discussion, methodology notes, confidence levels, and limitations.
- Scholarly evidence gathering as part of a broader research question: paper database searches, DOI / PMID / arXiv metadata checks, open-access clues, and bibliography validation.
- Verification of claims across multiple sources.
- A research plan before execution.
- A synthesis that distinguishes strong evidence, weak evidence, unresolved contradictions, and open questions.
Do not use this skill for:
- Quick factual lookup or a single-source summary.
- Lightweight single-paper lookup, pure arXiv reading, or bibliography cleanup without a broader research synthesis.
- Homework coaching, Socratic tutoring, quiz sessions, or thesis supervision.
- Local document cleanup, bibliography-file management, or bulk folder organization.
- Ghostwritten academic submissions where the user intends to submit the report as their own work without attribution.
How to call
Follow the workflow in references/research-workflow.md.
-
Clarify the research task before collecting evidence. Ask two or three essential questions about the decision, depth, scope, timeframe, geography, audience, and source preferences.
-
Restate the research objective. Confirm the interpreted question, intended output, and known constraints. Wait for the user's correction or confirmation when the scope is ambiguous.
What ships with it
6 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.
- 2mo ago First seen · 186 lines · 3 tokens per session scan A 965194aab8b0
deep-research is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (15 stars, last pushed 4mo ago), licensed MIT. It adds 3 tokens to every session and 1,820 once invoked, about $0.0000 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.
deep-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-researchOrkas-AI/Orkas-Awesome-AgentSkills | Skill | 15 | 4mo ago | MIT | A | 3 | Claude Code, Codex |
| check-mcp-jsontoolsdk-ai/toolsdk-mcp-registry | Skill | 220 | 4d ago | MIT | A | 68 | Codex |
| Vizra ADK Evaluation Frameworkvizra-ai/vizra-adk | Skill | 296 | 29d ago | MIT | A | 26 | Claude Code, Codex |
| Vizra ADK Workflowsvizra-ai/vizra-adk | Skill | 296 | 29d ago | MIT | A | 24 | Claude Code, Codex |
| bailian-train-deploymodelstudioai/skills | Skill | 59 | yesterday | Apache-2.0 | A | 321 | Claude Code, Codex |
| vox-video-directormodelstudioai/skills | Skill | 59 | yesterday | Apache-2.0 | A | 238 | Codex |
| spark-video-castmodelstudioai/skills | Skill | 59 | yesterday | Apache-2.0 | A | 66 | Claude Code, Codex |