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 mlopscommunity/Coding-Agents-Conference-skills --skill product-researchgit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-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/mlopscommunity/coding-agents-conference-skills/product-research)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/product-research"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/product-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/mlopscommunity/coding-agents-conference-skills/product-research"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/product-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 | $0.00043 | $0.01742 |
| Opus 5.5 | $0.00017 | $0.00697 |
| Sonnet 5.5 | $0.00009 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
product-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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Research with Claude Code
Overview
Two-phase technique for deep product research. First, offload broad information gathering to cheaper deep-research tools (Perplexity, ChatGPT Deep Research). Then feed those raw findings into Claude Code for synthesis, gap analysis, and strategic recommendations.
Core principle: Claude Code with web access is like having 100 researchers on staff. Give it big, open-ended questions. Brain-dump every open question you have stream-of-consciousness. The agent thrives on breadth -- let it surprise you with what it surfaces.
Dependency: Web search access (Claude Code with web tools, or pre-gathered research documents to feed in).
When to Use
- Entering a new market and need competitor landscape mapped
- Preparing for a sales call and need customer org charts, stakeholder priorities, and pain points
- Evaluating build-vs-buy decisions and need feature comparisons across vendors
- Running a quarterly strategy review and need market trends synthesized
- Exploring a new product direction and have dozens of unanswered questions
When NOT to Use
- You need a single factual answer (just search directly)
- The research requires proprietary databases or paywalled sources Claude cannot access
- You need legally verified claims (agent research is a starting point, not a legal opinion)
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Asking narrow, specific questions one at a time | You lose the agent's biggest strength: parallel exploration. Dump all your open questions at once and let it find connections you would not have thought of. |
| Running expensive Claude Code tokens on raw information gathering | Deep research tools like Perplexity and ChatGPT are cheaper for the gathering phase. Use Claude Code for the synthesis and strategic thinking, not the initial web crawling. |
| Treating agent output as verified fact | The agent surfaces leads and patterns. Always verify critical claims -- competitor pricing, customer org details, market size figures -- before acting on them. |
| Skipping the brain-dump and writing a polished brief instead | The messier and more complete your question dump, the better. The agent handles ambiguity well. A polished brief often omits the half-formed questions that lead to the best insights. |
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 · 168 lines · 43 tokens per session scan A 021d48d06ad6
product-research is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (39 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,742 once invoked, about $0.0002 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.
product-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-researchmlopscommunity/Coding-Agents-Conference-skills | Skill | 39 | 7mo ago | Apache-2.0 | A | 43 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |