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 tallesborges/zdx --skill deep-researchgit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/deep-research)<a href="https://agentmods.dev/skills/tallesborges/zdx/deep-research"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/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/tallesborges/zdx/deep-research"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/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 | $0.00015 | $0.00885 |
| Opus 5.5 | $0.00006 | $0.00354 |
| Sonnet 5.5 | $0.00003 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Use this skill only when the user explicitly asks for deep research.
This skill is provider-agnostic. Choose the provider or implementation that best fits the user's request and the available environment.
Typical triggers:
- Market or competitor research
- Broad landscape scans
- "Do deep research on X"
- Requests for a long-form, cited report
- Questions that need multi-hop web exploration across many sources
Do not use this skill for:
- Simple current-event lookups
- Fetching one known page
- Narrow factual questions that
web_searchcan answer quickly - Tasks that mainly need repo/file analysis instead of web research
Default approach
If the user does not specify a provider, use the bundled default implementation in scripts/parallel_deep_research.py.
The bundled script:
- creates a deep research run
- uses the default fast/cheap configuration
- polls until completion
- prints the final result to stdout
- can save raw JSON and report artifacts under
$ZDX_ARTIFACT_DIR
If the user explicitly wants another provider for deep research, follow that provider instead of the bundled default implementation.
Recommended workflow
- Decide if deep research is actually warranted.
- If yes, choose the provider/implementation.
- Write a strong research prompt.
- Run the deep research flow.
- Read the result.
- Summarize the findings for the user, keeping key citations/limitations.
Prompt writing guidance
Good prompts are specific about:
- topic and scope
- geography/timeframe
- what comparisons matter
- desired output style
- what to emphasize or exclude
Good example:
Create a research report on the current landscape of developer-focused AI coding agents in 2026. Compare product positioning, core workflows, pricing signals, platform support, and notable technical differentiators. Focus on official product pages, docs, benchmark posts, and credible reporting. End with a concise competitive summary.
Weak example:
Research AI coding tools.
What ships with it
1 file 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.
- 1mo ago First seen · 133 lines · 15 tokens per session scan A 6e1f0481a169
deep-research is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 885 once invoked, about $0.0001 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…