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 sergekostenchuk/ui-ux-agent-skill-system --skill serp-keyword-harvestergit clone --depth 1 https://github.com/sergekostenchuk/ui-ux-agent-skill-systemWrote 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/sergekostenchuk/ui-ux-agent-skill-system/serp-keyword-harvester)<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/serp-keyword-harvester"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/serp-keyword-harvester/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/sergekostenchuk/ui-ux-agent-skill-system/serp-keyword-harvester"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/serp-keyword-harvester.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 | $0.00064 | $0.00763 |
| Opus 5 | $0.00032 | $0.00381 |
| Sonnet 5 | $0.00013 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
serp-keyword-harvester 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SERP Keyword Harvester
This skill prepares raw search-demand evidence for the pre-design pipeline. It does not decide final site architecture or source/proxy policy; serp-source-configurator owns setup gates and this skill hands structured inputs to semantic-core-builder.
Operating Modes
plan: define seed keywords, locales, sources, approvals, and fallback.harvest-local: normalize user-provided keywords, exported CSVs, existing site text, or local reports.harvest-external: use approved SERP/autocomplete APIs or tools; approval required before network calls.audit: review an existingreports/keyword-harvest.json.
Required Workflow
- Read references/keyword-harvest-contract.md.
- If OpenSERP, AKE, proxy, API keys, engine checkboxes, source settings, or paid-proxy limits are mentioned, route setup to
serp-source-configuratorfirst and consume its redactedreports/serp-source-config.jsonhandoff. - If OpenSERP is already approved/configured, read references/openserp-setup.md and use assets/openserp-settings.example.json only as a redacted contract, not as a credential store.
- Confirm privacy and approval mode:
- local inputs and user-provided public facts: allowed;
- external SERP/API/crawling: explicit approval required;
- private/authenticated sources: explicit approval plus data-handling note.
- Collect or normalize seed keywords, market/locale, project type, and source provenance.
- Write or update
reports/keyword-harvest.jsonusing assets/keyword-harvest.schema.json as the field contract. - Label every data group as
Ran,Skipped,Planned, orManual. - Hand off to
semantic-core-builder; do not invent missing SERP evidence.
Safety Rules
- Do not scrape or call external services without approval.
- Do not store API keys, cookies, private URLs, recovery codes, or
.envvalues in reports. - Treat OpenSERP as
optional-cloud/external-network: no call without explicit approval, configured credentials, query scope, source config, and a data-transfer note. - Do not decide proxy provider, paid budget, or engine selection inside this skill when it is not already explicit; use
serp-source-configurator. - If search APIs return 429/503 or are unavailable, mark the source
Skippedand continue with local/user-provided inputs.
What ships with it
5 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.
- 12d ago First seen · 61 lines · 64 tokens per session scan A bd34a7465bb5
serp-keyword-harvester is a skill published in the GitHub repository sergekostenchuk/ui-ux-agent-skill-system (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 763 once invoked, about $0.0003 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…