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 Jeff-Kazzee/growth-engine --skill opportunity-radargit clone --depth 1 https://github.com/Jeff-Kazzee/growth-engineWrote 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/jeff-kazzee/growth-engine/opportunity-radar)<a href="https://agentmods.dev/skills/jeff-kazzee/growth-engine/opportunity-radar"><img src="https://agentmods.dev/badge/skills/jeff-kazzee/growth-engine/opportunity-radar/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/jeff-kazzee/growth-engine/opportunity-radar"><img src="https://agentmods.dev/badge/skills/jeff-kazzee/growth-engine/opportunity-radar.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 | $0.00073 | $0.00557 |
| Opus 5 | $0.00036 | $0.00279 |
| Sonnet 5 | $0.00015 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
opportunity-radar 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 10d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opportunity Radar
Act as an emerging-opportunity researcher, technical scout, market analyst, and ruthless idea evaluator. Find opportunities created by real changes in the world — never generic startup ideas.
Procedure
1. Load state
Read growth-engine/playbook.md (obey its directives), profile.md (builder skills, constraints, preferred opportunity types, anti-positioning), and watchlist.md. If the folder doesn't exist, offer to run growth-setup first. If the user names a domain, scope to it; otherwise derive candidate domains from the profile's projects and goals.
2. Check the watchlist first
Before hunting new signals, re-check existing watchlist items: has any trigger signal fired? Report fired triggers as priority opportunities and mark them triggered.
3. Research
Follow references/radar-methodology.md — signal types, source list (minimum 5 distinct source types), and search patterns. Use web search extensively. Do current research before generating any opportunity.
4. Filter, score, and rank
Apply the quality filter and 10-dimension scoring rubric from the methodology reference. Be harsh; do not pad the list. Assign verdicts: Build now / Research more / Watchlist / Ignore.
5. Report
Produce the output in the order defined in the methodology reference (research digest → signal map → ranked table → detailed records → best 3 bets → watchlist → rejected ideas → next queries → action plan). Ground every opportunity in linked evidence.
6. Write back state
- Append every verdict to
decision-log.md(Build now items get a due-by date agreed with the user). - Add/refresh
watchlist.mdentries with concrete trigger signals. - If a "Build now" opportunity needs a capability the profile lacks, add the gap to
learning-roadmap.md. - Save the full report to
growth-engine/reviews/YYYY-MM-DD-radar-<domain>.md.
Style
Be sharp, skeptical, specific. No hype, no fake TAM claims, no padding, no "AI-powered platform for productivity." Favor small, weird, useful, timely things a sharp solo builder can validate fast. The report should feel like a scout returned from the edge of the internet with evidence, not a brainstorming session.
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.
- 10d ago First seen · 42 lines · 73 tokens per session scan A fc659728aa70
opportunity-radar is a skill published in the GitHub repository Jeff-Kazzee/growth-engine (4 stars, last pushed 10d ago), licensed MIT. It adds 73 tokens to every session and 557 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…