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 olelehmann1337/workshop-plugin --skill keywordresearch-workshop-v2git clone --depth 1 https://github.com/olelehmann1337/workshop-pluginWrote 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/olelehmann1337/workshop-plugin/keywordresearch-workshop-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/keywordresearch-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/keywordresearch-workshop-v2.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 5.1 | $0.00107 | $0.06197 |
| Opus 5 | $0.00053 | $0.03099 |
| Sonnet 5 | $0.00021 | $0.01239 |
| Haiku 4.5 | $0.00011 | $0.00620 |
Grade A, and why
keywordresearch-workshop-v2 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 7d 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 — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keyword Research
Most keyword research dies in a spreadsheet because it starts with the tool, not the buyer. This skill flips that: pull the language from the business and the audience first, then expand outward through six angles, then score every cluster against opportunity AND revenue before a single article gets written. The output is a ranked content plan with a clear first move — not a 500-row CSV nobody opens twice.
the core job
What this produces: A scored content plan containing keyword clusters sorted into topic anchors, ranked on real opportunity, matched to specific content formats, and topped with one explicit first-move recommendation.
Output format: Markdown deliverable with four sections — (1) summary of biggest opportunities + first move, (2) anchor detail tables with intent and format per cluster, (3) 90-day publishing calendar, (4) optional appendix of full keyword universe organized by anchor. See output format section below for the exact template.
before starting: gather context
STOP. Do not produce keyword research until context is in hand. Cap questions at 2 max.
Step A: Gather context (fast)
Keyword research needs two dimensions from context: ICP (their language IS the keyword list) and business (what maps to offers). Voice is not needed here.
- Check CLAUDE.md first. Claude auto-loads
~/.claude/CLAUDE.mdand any project-levelCLAUDE.md. Scan for audience pain, exact phrases they use, products, services, content pillars. - If missing, check the project folder for
Context/icp.mdandContext/business.md. Read whichever exist. - If audience is still unclear after both: ask inline, don't guess. The ICP's language IS the research output.
Step B: Confirm the brief (≤2 questions, combined)
Skip anything CLAUDE.md or Context/ files cover. Prioritize and combine into at most 2 questions:
- Offer + audience + website — "What's being sold, to whom, and what's the current URL?" (combine into one question)
- Goal + competitors + timeline — "Goal (traffic, leads, sales, authority), two or three competitors if you have them, and quick wins vs. long-term?" (combine)
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.
- 7d ago First seen · 521 lines · 107 tokens per session scan A 1f715098a5d6
keywordresearch-workshop-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 6,197 once invoked, about $0.0005 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…