Borrowing it
Nothing to install: this file belongs to fenjo26/OpenGSC. 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/fenjo26/OpenGSC/main/.agents/skills/keyword-research/SKILL.mdgit clone --depth 1 https://github.com/fenjo26/OpenGSCWrote 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/fenjo26/opengsc/keyword-research)<a href="https://agentmods.dev/skills/fenjo26/opengsc/keyword-research"><img src="https://agentmods.dev/badge/skills/fenjo26/opengsc/keyword-research/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/fenjo26/opengsc/keyword-research"><img src="https://agentmods.dev/badge/skills/fenjo26/opengsc/keyword-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 96 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 97 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.01328 |
| Opus 5 | $0.00026 | $0.00664 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
keyword-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 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenGSC Keyword Research
Goal
Produce a short list of keywords the user should act on, each one labelled with what the action actually is — improve an existing page, fix an intent mismatch, or write something new. Volume alone is not a plan.
The free path comes first
Only one tool here spends money, and most research questions are answered without it. Work in this order and stop as soon as the answer is good enough:
- Queries the site already earns.
get_search_performance,get_striking_distance. - Research already bought.
get_keyword_demand— a seed researched in the last 14 days comes back at no cost, and with no seed it lists everything already stored. - Metrics already cached.
get_keyword_metricsfor volume/difficulty on a fixed list. - Only then
research_keywords, which is PAID and needs explicit permission.
An agent that opens with the paid tool has skipped three sources of the same information.
Required inputs
- The site. If unknown, call
list_sitesfirst and ask which one. - One or more seed topics, products, or audience problems.
- Optional: market (2-letter country code, default
us) and language.
If the market would materially change the numbers and the user has not said, ask. A German
market research run against us is not a smaller answer, it is a wrong one.
OpenGSC MCP tools
get_striking_distance: queries at positions 4–20 with real impressions. This is demand the site has already proven it can reach — it outranks anything discovery returns.get_keyword_demand: stored research joined against the site's own GSC positions. Every row carries a verdict (see below). Free. Call before anything paid.get_keyword_metrics: volume, difficulty and CPC for a known keyword list, from the cache the UI and CSV imports fill. A keyword missing here has not been loaded — that is not zero volume.research_keywords: PAID. DataForSEO discovery from one seed, verdicted against GSC. ~$0.03 per call at the default 150 rows. Requiresconfirm: true.get_competitor_gap: keywords competitors rank for, bucketed the same way. Free, but only returns rows if a competitor has already been pulled in the Competitors screen.get_content_groups: if the user has Content Groups or Topic Clusters, map findings onto them — it is how they already think about the site.get_generations: what has already been written. Recommending a page that exists wastes the user's time and makes the rest of the report look unchecked.
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 · 106 lines · 52 tokens per session scan A 82b40189db16
keyword-research is a skill published in the GitHub repository fenjo26/OpenGSC (22 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,328 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
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
copilotkit-setup
Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…