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 JAICHANGPARK/workshop-harness --skill workshop-web-researchergit clone --depth 1 https://github.com/JAICHANGPARK/workshop-harnessWrote 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/jaichangpark/workshop-harness/workshop-web-researcher)<a href="https://agentmods.dev/skills/jaichangpark/workshop-harness/workshop-web-researcher"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/workshop-web-researcher/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/jaichangpark/workshop-harness/workshop-web-researcher"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/workshop-web-researcher.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 | $0.00066 | $0.01707 |
| Opus 5 | $0.00033 | $0.00853 |
| Sonnet 5 | $0.00013 | $0.00341 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
workshop-web-researcher 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workshop Web Researcher Skill
Purpose
AI model knowledge cutoffs can cause agents to reference obsolete tool versions, retired API model tags, or outdated SDK method signatures. This skill enforces a dynamic verification protocol that queries live web sources before generating any technical documentation or code.
Dynamic Discovery Protocol
Mandatory Verification Before Generation
Before writing any code, README, setup guide, or prompt pack that references software tools or AI models, the agent must:
- Query Official Release Sources: Search official GitHub release notes, PyPI, npm, or vendor documentation.
- Compare Against Training Data: Check if the agent's internal default matches the latest live release tag.
- Apply Verified Versions: Write the verified latest release version in all code imports and setup guides.
- Stamp Currency Label: Add a dynamic timestamp label at the top of generated markdown files:
> Latest tool and model release versions verified on: YYYY-MM-DD
Primary Verification Lookup Table
| Target Tool / Model | Primary Official Source URL | Example Query | Latest Recommended Tags (2026) |
|---|---|---|---|
| Google GenAI SDK | https://pypi.org/project/google-genai/ |
site:pypi.org google-genai latest SDK methods |
google-genai (Unified SDK) |
| Google Agent Development Kit (ADK) | https://cloud.google.com/vertex-ai/docs/agent-development-kit |
site:cloud.google.com agent development kit adk |
google-adk, google-genai-adk (Python, TS, Go) |
| Google Gemini API | https://ai.google.dev/gemini-api/docs/models/gemini |
site:ai.google.dev gemini model versions |
gemini-3.7-flash, gemini-3.5-flash, gemini-3.1-pro-preview |
| Google Gemini Live API | https://ai.google.dev/gemini-api/docs/live |
site:ai.google.dev gemini live api |
gemini-3.1-flash-live-preview, gemini-3.5-live-translate-preview |
| Flutter Gemini Live | https://pub.dev/packages/gemini_live |
site:pub.dev gemini_live flutter |
gemini_live (pub.dev direct WebSocket package) |
| Anthropic Claude API | https://docs.anthropic.com/en/docs/about-claude/models |
site:docs.anthropic.com claude models release |
claude-sonnet-5, claude-opus-5, claude-fable-5 |
| OpenAI API | https://platform.openai.com/docs/models |
site:platform.openai.com/docs/models latest |
gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna |
| Ollama | https://github.com/ollama/ollama/releases |
site:github.com/ollama/ollama releases latest |
ollama latest engine |
| Gemma Models | https://ollama.com/library/gemma |
site:ollama.com/library gemma release tags |
gemma4, gemma:latest |
| LangChain / LangGraph | https://github.com/langchain-ai/langchain/releases |
site:github.com/langchain-ai/langchain releases latest |
langchain>=0.3, langgraph |
| LM Studio | https://github.com/lmstudio-ai/lms/releases |
site:github.com/lmstudio-ai/lms releases |
lms CLI latest |
| Astral uv | https://github.com/astral-sh/uv/releases |
site:github.com/astral-sh/uv releases |
uv package manager |
| Docker Engine | https://docs.docker.com/engine/release-notes/ |
docker engine release notes latest |
Latest official Docker Engine |
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 · 87 lines · 66 tokens per session scan A d03d4d7419c9
workshop-web-researcher is a skill published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 1,707 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 2026-08-31.
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…