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 bahayonghang/my-ai-cli-toolkit --skill deep-research-progit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/deep-research-pro)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/deep-research-pro"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/deep-research-pro.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01094 |
| Opus 5 | $0.00039 | $0.00547 |
| Sonnet 5 | $0.00016 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
deep-research-pro 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Pro
Use this skill to turn an open-ended topic into a grounded, cited research deliverable. The goal is not to dump links. The goal is to answer the user's real question with evidence, recency awareness, and explicit uncertainty.
When to use
Use this skill when the user wants:
- current information
- topic comparison or landscape mapping
- a cited briefing, memo, or report
- decision support backed by multiple sources
- research on markets, companies, policy, science, or technology
Do not use this skill when:
- the task is purely local to the repo or codebase
- the user explicitly says not to browse
- the user only wants a quick opinion with no sourcing
Workflow
1. Lock the research objective
Extract or infer:
- topic
- user goal: learn, decide, write, compare, or monitor
- preferred depth: quick brief, standard report, or deep dive
- expected output: chat answer, outline, memo, or saved file
Ask at most 1-2 clarifying questions only if the answer would materially change the search plan or final deliverable. If not, proceed with reasonable defaults and state them.
2. Break the topic into sub-questions
Create 3-5 sub-questions that cover the topic from different angles, such as:
- definition and scope
- current state and recent developments
- evidence, metrics, or outcomes
- major players or competing schools
- risks, limitations, or open questions
Do not search blindly for the top-level topic only.
3. Search with source discipline
Use the current environment's available web tools. Prefer primary and high-signal sources in this order:
- official documentation, regulators, standards bodies, company filings, papers, or datasets
- reputable journalism or domain publications
- expert analysis and industry commentary
For each sub-question:
- try 2-3 focused query variants
- collect multiple independent sources
- prefer recent sources when the topic is time-sensitive
- capture source title, publisher, URL, and date
What ships with it
2 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.
- 8d ago First seen · 162 lines · 79 tokens per session scan A 54b5ce1651bd
deep-research-pro is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,094 once invoked, about $0.0004 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
research-agent
Multi-source deep research with synthesis and inline citations. Use when user asks to research a topic, compare technologies, do competitive analysis, or investigate a subject in depth.
Web Research Report
Synthesize fetched web sources into a structured research report on a topic: key findings, themes, tradeoffs, and a recommendation, with citations. Use for web research, literature review, and report writing.
research-ops
Use when someone hands you an open question whose answer must survive scrutiny — a tech choice, a regulation, a what-is-actually-true-about-X — with every non-obvious claim dated and sourced, source disagreements surfaced rather than averaged away, and a cited memo as the deliverable. Also for refreshing a stale…
lit-review-assistant
Search, summarize, and synthesize economics literature.
sources-section
Appends a Sources/References section using only web sources from the sources pool.
research-synthesis
Web research and synthesis using agy CLI.