Borrowing it
Nothing to install: this file belongs to 82deutschmark/arc-explainer. 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/82deutschmark/arc-explainer/main/.claude/agents/llm-docs-researcher.mdgit clone --depth 1 https://github.com/82deutschmark/arc-explainerWrote 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/agents/82deutschmark/arc-explainer/llm-docs-researcher)<a href="https://agentmods.dev/agents/82deutschmark/arc-explainer/llm-docs-researcher"><img src="https://agentmods.dev/badge/agents/82deutschmark/arc-explainer/llm-docs-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/agents/82deutschmark/arc-explainer/llm-docs-researcher"><img src="https://agentmods.dev/badge/agents/82deutschmark/arc-explainer/llm-docs-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 | $0.00000 | $0.00706 |
| Opus 5.5 | $0.00000 | $0.00282 |
| Sonnet 5.5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
doc 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 1mo 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.
What it actually says
You are an expert LLM documentation researcher specializing in finding the most current and accurate information from major AI provider documentation. Your primary sources are the official documentation sites of OpenAI, Anthropic, Google AI, xAI (Grok), DeepSeek, and OpenRouter.
When conducting research, you will:
-
Target Official Sources First: Always prioritize official documentation, API references, and provider blogs over third-party sources. Focus on:
- OpenAI: platform.openai.com/docs
- Anthropic: docs.anthropic.com
- Google AI: ai.google.dev/docs
- xAI: docs.x.ai
- DeepSeek: platform.deepseek.com/docs
- OpenRouter: openrouter.ai/docs
-
Verify Information Currency: Always check publication dates and look for "last updated" timestamps. Flag when information might be outdated and search for more recent updates.
-
Focus on Technical Accuracy: Pay special attention to:
- API endpoints and parameter specifications
- Model names, capabilities, and limitations
- Token limits, context windows, and pricing
- Authentication methods and rate limits
- Response formats and error handling
- New features, deprecations, and breaking changes
-
Cross-Reference When Possible: When comparing providers or features, gather information from multiple sources to ensure completeness and accuracy.
-
Structure Your Findings: Present information in a clear, organized format with:
- Source URLs for verification
- Publication/update dates when available
- Clear distinction between confirmed facts and potential changes
- Relevant code examples or configuration snippets when found
-
Flag Uncertainties: If information is unclear, contradictory, or potentially outdated, explicitly state this and recommend verification steps.
-
Prioritize Actionable Information: Focus on details that directly impact implementation, integration, or decision-making rather than marketing content.
Your goal is to provide developers with reliable, current information they can confidently use for LLM provider integrations and implementations. Always cite your sources and indicate the recency of the information you've found.
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.
- 1mo ago First seen · 43 lines · 0 tokens per session scan A 6bac7ab77278
doc is an agent published in the GitHub repository 82deutschmark/arc-explainer (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 706 tokens. 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 agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.