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 agentmods add skills/mo-root/open-kb/mapping-marketsnpx skills add mo-root/open-kb --skill mapping-marketsgit clone --depth 1 https://github.com/mo-root/open-kbWrote 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/mo-root/open-kb/mapping-markets)<a href="https://agentmods.dev/skills/mo-root/open-kb/mapping-markets"><img src="https://agentmods.dev/badge/skills/mo-root/open-kb/mapping-markets.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 | $0.00134 | $0.02143 |
| Opus 5 | $0.00067 | $0.01071 |
| Sonnet 5 | $0.00027 | $0.00429 |
| Haiku 4.5 | $0.00013 | $0.00214 |
Grade A, and why
mapping-markets 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 4d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapping a market from one domain
You give it stripe.com. It reads Stripe's own pages to work out what Stripe sells, groups those
products into the distinct markets they sit in, writes search queries that describe those markets
without ever naming Stripe, fires them, and classifies every host that comes back.
The output is a map: companies, products, communities, publishers and directories, each with what it is, how it relates to the anchor, and why.
When you reach for this
Someone has a company and wants the shape of the world around it. "Who competes with us." "What are the alternatives to X." "Where do our buyers actually hang out." "Who writes about this space." "Give me a target list." Also when they have a company they are evaluating and want its landscape rather than its pitch.
Not for researching a single company in depth — this maps outward from one, it does not profile it.
The one idea
The catalog is written before any company name is known. The queries describe what the anchor does, never what it is called, so a look-up query is structurally impossible to write. That is why the map contains companies nobody had heard of rather than the five names already on the first page of Google.
The corollary matters when you read the output: a competitor here is something the search put next to the anchor, not something a human already knew about.
The shape of the work
Market map progress:
- [ ] 1. Credentials resolve
- [ ] 2. Agree the depth, because depth is the bill
- [ ] 3. Run it, watching the phase log
- [ ] 4. Read the map back and say what it found
- [ ] 5. Say plainly which parts to trust
Do not skip 5. See "How much to trust it" below — it is measured, not a disclaimer.
Step 1 — Credentials
Four, in a .env at the repo root:
| Variable | What it is |
|---|---|
BRIGHTDATA_API_TOKEN |
Bright Data account API token |
BRIGHTDATA_SERP_ZONE |
name of a SERP API zone |
BRIGHTDATA_UNLOCKER_ZONE |
name of a Web Unlocker zone |
OPENROUTER_API_KEY |
LLM key. Note the key's own limit, not just the account balance |
What ships with it
3 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.
- 4d ago First seen · 180 lines · 134 tokens per session scan A f50ba9a9c85f
mapping-markets is a skill published in the GitHub repository mo-root/open-kb (11 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 2,143 once invoked, about $0.0007 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
competitor-research-playbook
Your competitor just launched. You have no idea how they grew so fast. Should you reverse-engineer their website? Track their social media? Map their growth flywheel? This gives you the complete SOP — from Wayback Machine snapshots to X/Twitter propagation analysis to growth flywheel scoring. Built from 150+ AI…
gr-competitor-research
Your competitor just launched. You have no idea how they grew so fast. Should you reverse-engineer their website? Track their social media? Map their growth flywheel? This gives you the complete SOP — from Wayback Machine snapshots to X/Twitter propagation analysis to growth flywheel scoring. Built from 150+ AI…
gr-competitor
竞品深度扫描。批量抓取对手落地页(title/h1/intro/pricing)、定价页、博客 top 10、 变更历史(Wayback)。底层调 actionbook(并发 30 tab + 省 90% token)。 当用户说"分析对手"、"看看竞品在做啥"、"找对标"、"扫一下 top 10"时调用。.
falsify
Adversarial falsification of sigint research findings. Generates disconfirming queries, executes web-only adversarial search, assigns ordinal verdicts (falsified | weakened | survived | inconclusive), and applies remediation (quarantine, confidence downgrade, follow-up queue). Invocable standalone via /sigint:falsify…
regulatory-review
This skill should be used when the user asks to "analyze regulations", "regulatory landscape", "compliance requirements", "legal considerations", "regulatory risk", "industry regulations", "compliance analysis", "regulatory trends", or needs guidance on understanding regulatory environments, compliance requirements…
tech-assessment
This skill should be used when the user asks to "assess technology", "technology evaluation", "tech stack analysis", "technical feasibility", "technology trends", "build vs buy", "technology roadmap", "architecture assessment", or needs guidance on evaluating technologies, technical due diligence, or technology…