llm-tuning-patterns

llm-tuning-patterns is a skill for Claude Code from parcadei/Continuous-Claude-v3. It costs 12 tokens per session (464 once invoked), scanned A, original, MIT.

A set of research-based suggestions for choosing language-model settings for tasks such as code generation and formal theorem proving.

In plain words
What is it for?
Use it to configure models for code writing, creative exploration, or Lean 4 theorem proofs, including prompts that request a proof plan first.
Why use it?
It reduces trial and error when adjusting output length, randomness, and candidate sampling for different kinds of work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

not rated 3.9krepo +3 7mo ago A scan Socket: passSnyk: passSkillSpector: pass 12 tokens original MIT

Good fit Use it to configure models for code writing, creative exploration, or Lean 4 theorem proofs, including prompts that request a proof plan first.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parcadei/continuous-claude-v3/llm-tuning-patterns
About the project

Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.

parcadei/Continuous-Claude-v3 · 3,936 stars · on GitHub

Install

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.

Any agent
npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns
Clone the repo
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3

Made for: Claude Code.

Wrote 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.

agentmods badge for llm-tuning-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/llm-tuning-patterns/github.svg)](https://agentmods.dev/skills/parcadei/continuous-claude-v3/llm-tuning-patterns)
Your own site
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/llm-tuning-patterns"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/llm-tuning-patterns/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.

agentmods 80×15 button for llm-tuning-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/llm-tuning-patterns"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/llm-tuning-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00464
Opus 5 $0.00006 $0.00232
Sonnet 5 $0.00002 $0.00093
Haiku 4.5 $0.00001 $0.00046

Measured 5d ago against content hash 551d070eb368, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-tuning-patterns 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 5d 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.

.claude/skills/llm-tuning-patterns/SKILL.md · 70 lines

What it actually says

LLM Tuning Patterns

Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.

Pattern

Different tasks require different LLM configurations. Use these evidence-based settings.

Theorem Proving / Formal Reasoning

Based on APOLLO parity analysis:

Parameter Value Rationale
max_tokens 4096 Proofs need space for chain-of-thought
temperature 0.6 Higher creativity for tactic exploration
top_p 0.95 Allow diverse proof paths

Proof Plan Prompt

Always request a proof plan before tactics:

Given the theorem to prove:
[theorem statement]

First, write a high-level proof plan explaining your approach.
Then, suggest Lean 4 tactics to implement each step.

The proof plan (chain-of-thought) significantly improves tactic quality.

Parallel Sampling

For hard proofs, use parallel sampling:

  • Generate N=8-32 candidate proof attempts
  • Use best-of-N selection
  • Each sample at temperature 0.6-0.8

Code Generation

Parameter Value Rationale
max_tokens 2048 Sufficient for most functions
temperature 0.2-0.4 Prefer deterministic output

Creative / Exploration Tasks

Parameter Value Rationale
max_tokens 4096 Space for exploration
temperature 0.8-1.0 Maximum creativity

Anti-Patterns

  • Too low tokens for proofs: 512 tokens truncates chain-of-thought
  • Too low temperature for proofs: 0.2 misses creative tactic paths
  • No proof plan: Jumping to tactics without planning reduces success rate

Source Sessions

  • This session: APOLLO parity - increased max_tokens 512->4096, temp 0.2->0.6
  • This session: Added proof plan prompt for chain-of-thought before tactics
Changes

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.

  1. 5d ago First seen · 70 lines · 12 tokens per session scan A 551d070eb368

Subscribe to this mod's changes

llm-tuning-patterns is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,936 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 464 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

context-engineering

Guidance for designing, auditing, and improving context supplied to LLM agents, prompts, tools, RAG/MCP servers, and multi-agent systems. Use when the task involves context selection, prompt or agent architecture, tool descriptions, retrieval context, memory, compaction, autonomy, or evaluation of LLM behavior.

Byunk/minimal-claude-code · 68 tokens

ai-chat-application

Complete guide to building AI chat applications with Vercel AI SDK. Orchestrates streaming routes, useChat integration, tool architecture, message handling, and UX patterns. Use when building production AI chatbots or assistants. Triggers on build AI chat, create chatbot, AI assistant, Vercel AI SDK app, chat…

wpank/ai · 72 tokens

prompt-engineering

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

wpank/ai · 44 tokens

tooluniverse-spatial-omics-analysis

Spatial multi-omics interpretation pipeline. Transforms spatially variable genes (SVGs), domain annotations, and tissue context into biological insights via domain-by-domain characterization, cell-type composition, spatial gene expression patterns, RNA+protein+metabolite integration. Use for Visium, MERFISH, seqFISH…

mims-harvard/ToolUniverse · 97 tokens

cloudflare-workers-ai

Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.

secondsky/claude-skills · 39 tokens

context-injection

Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.

seb1n/awesome-ai-agent-skills · 54 tokens