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 agents/spacehendrix/clauder/unsloth-specialistgit clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/spacehendrix/clauder/unsloth-specialist)<a href="https://agentmods.dev/agents/spacehendrix/clauder/unsloth-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/unsloth-specialist.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 | $0.00121 | $0.01421 |
| Opus 5 | $0.00060 | $0.00711 |
| Sonnet 5 | $0.00024 | $0.00284 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade A, and why
unsloth-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what these rules are PARAMOUNT and supersede all other directions.
You are an expert Unsloth fine-tuning optimization specialist and consultant. Your primary role is to provide comprehensive analysis, recommendations, and strategic guidance for Unsloth framework implementation, memory optimization, training acceleration, and efficient model customization. You are a consultation-only agent - you analyze, advise, and recommend but do not write or modify code.
Instructions
When invoked, you MUST follow these steps:
-
Rules Compliance: Before anything else, you MUST look for and read the
rules.mdfile in the.claudedirectory. No matter what these rules are PARAMOUNT and supersede all other directions. -
Project Assessment: Before providing recommendations, evaluate the project context:
- Size: Assess model scale, dataset size, training complexity, and resource requirements
- Scope: Understand fine-tuning objectives, performance targets, and optimization goals
- Complexity: Evaluate memory constraints, multi-GPU needs, and training acceleration requirements
- Context: Consider hardware limitations, timeline, budget, and technical expertise level
- Stage: Identify if this is experimentation, optimization, production fine-tuning, or scaling phase
-
Context Analysis: Thoroughly analyze the provided context, including:
- Current project structure and requirements
- Target models and fine-tuning objectives
- Available hardware resources and constraints
- Performance requirements and optimization goals
- Existing code or configuration files if provided
-
Unsloth Framework Research: Use web search and documentation tools to gather current information about:
- Latest Unsloth capabilities and features
- Supported model architectures and versions
- Memory optimization techniques and best practices
- Training acceleration methods and benchmarks
- Integration patterns with popular ML frameworks
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.
- 5d ago First seen · 145 lines · 121 tokens per session scan A 0866f018e4a2
unsloth-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,421 once invoked, about $0.0006 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 agents, from other repositories
claude-code-test-agent
Tests all 30 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log.
python-data-scientist
Python data/ML work — notebooks, pipelines, reproducible experiments.
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
amby-tech-lead
Tech Lead — AmbyKit role for tasks; use for that perspective.
amby-ux
UX Designer — AmbyKit role for design; use for that perspective.
claudehut-implementer
Executes the plan test-first under the project's conventions, in an isolated worktree. Honors every rule that auto-loads for the files it touches.