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 ckorhonen/claude-skills --skill llm-advisorgit clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote 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/ckorhonen/claude-skills/llm-advisor)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/llm-advisor"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/llm-advisor/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/ckorhonen/claude-skills/llm-advisor"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/llm-advisor.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 | $0.00083 | $0.02537 |
| Opus 5 | $0.00042 | $0.01269 |
| Sonnet 5 | $0.00017 | $0.00507 |
| Haiku 4.5 | $0.00008 | $0.00254 |
Grade A, and why
llm-advisor 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 11d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Advisor
Use Simon Willison's llm CLI to consult other LLMs for second opinions, alternative perspectives, and expert advice on complex problems.
When to Use This Skill
Proactive Use (autonomous)
Use this skill proactively without being asked when:
- Stuck >15 minutes on a bug or problem
- Complex debugging with unclear root cause
- Architecture decisions with significant trade-offs
- Planning complex features that need validation
- Unfamiliar codebase/language where you need guidance
- Security-sensitive code (auth, crypto, input validation)
On-Demand Use (user requests)
Use when the user says:
- "Ask Gemini/GPT/Claude about X"
- "Get a second opinion on this"
- "What would GPT think about this approach?"
- "Check with another model"
Prerequisites
Installation
# Install llm CLI
brew install llm
# or
pip install llm
# Set up OpenAI API key
llm keys set openai
# Install Gemini plugin (optional)
llm install llm-gemini
llm keys set gemini
# Install Anthropic plugin (optional)
llm install llm-anthropic
llm keys set anthropic
Verify Setup
# Check available models
llm models
# Test a simple prompt
llm "Hello, what model are you?"
Model Selection (Current as of 2026)
OpenAI Models
| Use Case | Model | Command |
|---|---|---|
| Fast/cheap | gpt-4o-mini | llm -m gpt-4o-mini "question" |
| General purpose | gpt-4.1 | llm -m gpt-4.1 "question" |
| Complex reasoning | o4-mini | llm -m o4-mini -o reasoning_effort=high "question" |
| Deep reasoning | o3 | llm -m o3 "question" |
| Premium | gpt-4.1 | llm -m gpt-4.1 "question" |
Note: Check
llm modelsto see exactly which model IDs are installed. OpenAI model names change frequently. As of 2026,gpt-4.1is the flagship GPT ando3/o4-miniare the reasoning models.
Google Gemini Models
| Use Case | Model | Command |
|---|---|---|
| Fast general | gemini-2.0-flash | llm -m gemini-2.0-flash "question" |
| Advanced + thinking | gemini-2.5-pro | llm -m gemini-2.5-pro "question" |
| Long context (1M+) | gemini-2.5-pro | llm -m gemini-2.5-pro "question" |
| Deep reasoning | gemini-2.5-pro | llm -m gemini-2.5-pro -o thinking_budget=32000 "question" |
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.
- 11d ago First seen · 354 lines · 83 tokens per session scan A 0d6b4283d75d
llm-advisor is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 2,537 once invoked, about $0.0004 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.