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 h4vzz/awesome-ai-agent-skills --skill deep-researchgit clone --depth 1 https://github.com/h4vzz/awesome-ai-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/h4vzz/awesome-ai-agent-skills/deep-research)<a href="https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/deep-research"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-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/h4vzz/awesome-ai-agent-skills/deep-research"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/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 | $0.00036 | $0.01763 |
| Opus 5 | $0.00018 | $0.00881 |
| Sonnet 5 | $0.00007 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00176 |
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 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.
This is a copy
98% identical to deep-research — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
This skill enables an AI agent to perform rigorous, multi-step research on complex topics. Rather than returning a single search result, the agent decomposes the research question into sub-queries, gathers information from diverse source types (academic papers, industry reports, official documentation, news articles, and expert commentary), cross-references findings for consistency, and synthesizes everything into a structured, citation-backed report. The result is a thorough analysis that surfaces nuance, identifies conflicting viewpoints, and highlights knowledge gaps.
Workflow
-
Decompose the Research Query: Break the user's high-level question into 3-6 targeted sub-queries that cover distinct facets of the topic. Each sub-query should address a specific angle such as historical context, current state, key players, technical details, or future outlook. This ensures broad coverage rather than shallow retrieval from a single search.
-
Identify and Gather Sources: For each sub-query, search across multiple source categories: academic databases, official documentation, reputable news outlets, industry analyst reports, and community forums. Aim for at least 2-3 sources per sub-query. Record the URL, publication date, author, and a relevance score for each source to enable later prioritization.
-
Extract and Organize Key Findings: Read each source and extract the core claims, data points, statistics, and expert opinions. Organize findings into a structured outline grouped by theme or sub-query. Tag each finding with its source for traceability.
-
Cross-Reference and Validate: Compare findings across sources to identify consensus, contradictions, and gaps. Flag any claims that appear in only one source or that conflict with the majority of evidence. Note the recency and authority of each source when resolving disagreements.
-
Synthesize the Report: Combine validated findings into a coherent narrative. Structure the report with an executive summary, detailed sections for each theme, a discussion of limitations and open questions, and a full reference list. Use clear headings and bullet points for readability.
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 · 106 lines · 36 tokens per session scan A c878cbb59a7f
deep-research is a skill published in the GitHub repository h4vzz/awesome-ai-agent-skills (34 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,763 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to deep-research, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
cost-optimizer
Trigger when the user asks to audit Claude Code costs, reduce token spend, says "my Claude bill is too high", "optimize my CLAUDE.md", "why is this project burning tokens", or "/cost-optimizer". Scans a project for the common Claude Code cost leaks and returns a prioritized fix list.
excalidraw-architecture
Trigger when the user asks for an architecture diagram, says "draw the system", "update the architecture diagram", "give me an excalidraw of this codebase", or "/excalidraw-architecture". Generates or updates an Excalidraw JSON file at docs/architecture.excalidraw by reading the codebase's key entry points.
model-cost-compare
Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the…
openclaw-debugger
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.
growth-ideas
Describe your product or project and get three actionable growth ideas tailored to your stage.
meeting-notes
Paste raw meeting notes and get a clean summary with key decisions and action items.