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 hashgraph-online/awesome-codex-plugins --skill batch-product-researchgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/batch-product-research)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/batch-product-research"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/batch-product-research.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00461 |
| Opus 5 | $0.00020 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
batch-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 yesterday.
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.
What it actually says
Batch Product Research
Use this skill for 1-20 keywords.
Inputs
Accept:
- comma-separated keywords
- numbered lists
- a local file path containing keywords
Defaults:
- maximum 20 keywords per run
- report path:
./artifacts/launchfast/batch-research/report-[YYYY-MM-DD].html - csv path:
./artifacts/launchfast/batch-research/report-[YYYY-MM-DD].csv
Workflow
1. Normalize input
- trim whitespace
- deduplicate case-insensitively
- if there are more than 20 keywords, split into chunks of 20 and process chunk-by-chunk
2. Run balanced product research
- run
research_productsfor every keyword - prefer parallel tool calls where practical
- do not require delegation
3. Score each keyword
For each keyword compute:
- search volume
- total niche revenue
- average price
- average reviews
- average revenue per seller
- top-seller dominance
- estimated margin using conservative assumptions
- opportunity score and verdict
Use verdicts:
- VIABLE
- MARGINAL
- NOT RECOMMENDED
- ERROR
4. Optional deeper passes
For VIABLE or MARGINAL keywords only:
- run
research_products(... focus="financial") - optionally run
amazon_keyword_researchon the top 2-3 ASINs if keyword depth matters for the user’s goal
5. Present ranked results
Always include a comparison table first.
Then provide concise cards or sections for the strongest keywords.
6. Write artifacts when useful
If the user asked for files, or a file materially improves the result:
- write an HTML report
- write a CSV export
Keep the file generation deterministic. Prefer Python for CSV writing.
Output
At minimum return:
- number of keywords processed
- ranking table
- top recommendations
- artifact paths when files were written
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.
- yesterday First seen · 91 lines · 41 tokens per session scan A 9f885cf1f780
batch-product-research is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (935 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 461 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
hunt-business-logic
Hunting skill for business logic vulnerabilities. Built from 7 public bug bounty reports. Use when hunting business logic on any target.
ecommerce-product-manager
Expert E-commerce Product Manager with deep knowledge of online retail strategy, conversion optimization, marketplace operations, and platform-specific tactics for Amazon, Shopify, and Alibaba. Use when: ecommerce-strategy, product-launch, conversion-optimization, marketplace-management, pricing-strategy.
ecommerce-livestream-trainer
Expert-level E-commerce Livestream Trainer with deep knowledge of live selling techniques, platform operations (TikTok Shop, Taobao Live, JD Live), audience engagement, and sales conversion.
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
tiktok-shop-webhooks
Receive and verify TikTok Shop webhooks. Use when setting up TikTok Shop webhook handlers, debugging Authorization-header signature verification, or handling events like ORDERSTATUSCHANGE, PACKAGEUPDATE, RECIPIENTADDRESSUPDATE, PRODUCTSTATUSCHANGE, or SELLERDEAUTHORIZATION.