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 agentmods add skills/psd401/psd-claude-plugins/multi-model-researchnpx skills add psd401/psd-claude-plugins --skill multi-model-researchgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/multi-model-research)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/multi-model-research"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/multi-model-research.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 | $0.00055 | $0.01338 |
| Opus 5 | $0.00028 | $0.00669 |
| Sonnet 5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
multi-model-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 4d 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.
This is a copy
100% identical to multi-model-research — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Model Research Agent
Implements Karpathy's LLM Council pattern for superior research through parallel queries, peer review, and chairman synthesis.
Architecture
Geoffrey/Claude (Native Council Member):
- Routes simple vs complex queries
- Calls external API orchestrator (
research.py) - Provides my own research response
- Conducts peer review phase
- Requests GPT-5.1 synthesis (chairman)
- Saves final report to Obsidian
Python External API Orchestrator:
- Fetches responses from GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1
- Returns JSON with all external responses
- I handle all orchestration and synthesis
When to Use This Skill
Use multi-model research when:
- Complex analysis needed - Multiple perspectives valuable
- Factual verification critical - Cross-model validation
- Comprehensive coverage required - No single model sufficient
- Current information essential - Perplexity provides web grounding
- Contested topics - Benefit from diverse model perspectives
Simple vs Council Mode
Simple Mode (Perplexity only):
- Factual lookups
- Current events
- Quick research with citations
- Completes in <15 seconds
Council Mode (Full council):
- Comparative analysis
- Deep research
- Multiple perspectives needed
- Strategic questions
- Completes in <90 seconds
Workflow
Simple Query
User: "What are the latest developments in quantum computing?"
↓
I decide: Simple query (factual, current)
↓
I call: uv run scripts/research.py --query "..." --models perplexity
↓
I read: JSON response from Perplexity
↓
I format: Markdown report with citations
↓
I save: To Obsidian Geoffrey/Research folder
↓
I return: Summary to user with Obsidian link
Council Query
User: "Compare the AI strategies of OpenAI, Anthropic, and Google"
↓
I decide: Council query (comparative, complex)
↓
I call: uv run scripts/research.py --query "..." --models gpt,gemini,perplexity,grok
↓
I read: JSON with all external responses
↓
I provide: My own (Claude) research response
↓
I conduct: Peer review (each model ranks others)
↓
I request: GPT-5.1 chairman synthesis
↓
I format: Comprehensive markdown report
↓
I save: To Obsidian Geoffrey/Research folder
↓
I return: Summary with Obsidian link
What ships with it
9 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.
- 4d ago First seen · 187 lines · 55 tokens per session scan A 779aec6bc1c2
multi-model-research is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,338 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to multi-model-research, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…