Borrowing it
Nothing to install: this file belongs to Lengros/bennu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lengros/bennu/main/.claude/skills/market-scan/SKILL.mdgit clone --depth 1 https://github.com/Lengros/bennuWrote 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/lengros/bennu/market-scan)<a href="https://agentmods.dev/skills/lengros/bennu/market-scan"><img src="https://agentmods.dev/badge/skills/lengros/bennu/market-scan/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/lengros/bennu/market-scan"><img src="https://agentmods.dev/badge/skills/lengros/bennu/market-scan.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 | $0.00210 | $0.02298 |
| Opus 5 | $0.00105 | $0.01149 |
| Sonnet 5 | $0.00042 | $0.00460 |
| Haiku 4.5 | $0.00021 | $0.00230 |
Grade A, and why
market-scan 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/market-scan — hypothesis → coded market signal
Takes a product hypothesis and sweeps public sources for evidence, then returns coded, ranked, source-tagged signal. It does not run the experiment or make the decision — it gathers found text. The orchestrator fills the brief template below and delegates to a fresh research subagent (the "researcher" — it gets web tools and no drafting context).
The engine, repeated at every stage: found public text is hypothesis-SHAPING, never validating. It cannot conclude willingness-to-pay; only a dry-wallet / fake-door test or real interviews can. Absence of signal is itself a finding. A vendor's marketing, a firm's voice, and a homeowner's complaint are not your target user's voice.
Pairs with /evidence-ledger: market-scan produces signal → the ledger records it as a
signal row and decides (kill/pivot/double-down) only with a behavioural test.
Different from /deep-research (fan-out + adversarial fact-check → cited report):
market-scan adds the two-lens frame (§2), error-analysis coding of voices into ranked
failure modes (§4), and discovery honesty (found-text ≠ WTP, absence-as-finding,
selection-bias) — disciplines /deep-research has no reason to carry.
Argument (optional): the hypothesis in any convenient form (a sentence, bullets). If absent, use the bet under discussion.
1. Intake — normalize the loose ask
Pull these from the input; fill gaps with stated defaults, don't block on them:
- Hypothesis / premise — what we believe and want to confirm or kill.
- Product & segment — and precisely who the target user is (e.g. "SOLO/micro plumber", not "trades").
- Geo + language — search language(s); name them (the scan reads in that language).
- Lens —
supply,demand, orboth(§2). - Feeds which
/evidence-ledgerassumption — name the row(s) it informs. - Seeds — any known competitors / sources to start from.
2. The two lenses (one playbook)
- Supply — what solutions/competitors exist, their coverage of the job(s), pricing, and geo/language fit. Answers: is the "no convenient solution" premise true? Beware: a tool existing ≠ the target adopting it conveniently — say which you've shown.
- Demand — what real target users say about the pain in their own words. Answers: is this an acute, would-pay pain? Is there integration pain across current tools?
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.
- 9d ago First seen · 138 lines · 0 tokens per session scan A 16723bc435db
market-scan is a skill published in the GitHub repository Lengros/bennu (2 stars, last pushed 2mo ago), licensed MIT. It adds 210 tokens to every session and 2,298 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.