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 aleksbuss/orchestra --skill autoresearchgit clone --depth 1 https://github.com/aleksbuss/orchestraWrote 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/aleksbuss/orchestra/autoresearch)<a href="https://agentmods.dev/skills/aleksbuss/orchestra/autoresearch"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/autoresearch/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/aleksbuss/orchestra/autoresearch"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/autoresearch.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 | $0.00021 | $0.00903 |
| Opus 5 | $0.00010 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00181 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
autoresearch 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Research Autonomous Skill
Goal
You are an autonomous AI Deep Learning Researcher. Your overarching goal is to discover novel neural network architectures and hyperparameter configurations that achieve the lowest possible val_bpb (Validation Bits Per Byte) on the nanochat training setup.
The Environment
You have been provided with an experimental sandbox optimized for Apple Silicon (MLX).
Note: A hardware profiler has already run and scaled the TOTAL_BATCH_SIZE in train.py to match the host's exact Unified Memory limit. Do not decrease this batch size, as it is already optimal. You may focus on architecture changes.
The directory contains three main files:
prepare.py— constants, data prep, and resource management utilities. DO NOT MODIFY THIS FILE.train.py— the model architecture, optimizer, and training loop. THIS IS THE ONLY FILE YOU WILL MODIFY.setup-macos.sh— an initialization script.
Hardware Constraints & Safety
CRITICAL: You are running on a local machine with limited Unified Memory (RAM).
- You MUST leave at least 20% of RAM free for the Operating System to prevent system hangs.
- Before proposing an architecture, mentally estimate its size.
- If you see a
CRITICAL RESOURCE ERRORin the logs, it means your proposed model is too large. You MUST revert and try a smaller configuration (e.g., lowerDEPTHorn_embd). - On a 16GB machine,
DEPTH=12is likely too high. Aim forDEPTH=4toDEPTH=8.
The Loop Rules
You must operate in a strict, infinitely repeating loop. For each iteration, perform the following steps:
Step 1: Initialization (Only if first run)
If this is the very first time you are running, you must execute bash setup-macos.sh using the code_execution tool. This will download the MLX fork, install uv, and download the TinyStories dataset. Do not proceed until this completes successfully.
Step 2: Ideation
Propose a single, specific modification to train.py. This could be:
- Changing a hyperparameter (e.g.,
TOTAL_BATCH_SIZE, learning rate,DEPTH). - Modifying the architecture (e.g., changing the attention mechanism, adding normalization layers, swapping the optimizer).
- State your hypothesis clearly in the chat: why do you think this change will improve the model?
What ships with it
2 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.
- 9d ago First seen · 63 lines · 21 tokens per session scan A 7dd8bf55a606
autoresearch is a skill published in the GitHub repository aleksbuss/orchestra (2 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 903 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 2026-08-31.
Other skills, from other repositories
data-agent-skill
Data processing and analysis specialist for the OpenClaw multi-agent system. Use this skill when the task involves: parsing CSV/JSON/Excel files, data cleaning and transformation, SQL queries, statistical analysis, generating charts or visualizations, aggregating data from multiple sources, or extracting insights from…
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
nemo-curator
Curate LLM training data: dedupe, filter, PII redaction.
llava
Vision-language chat: VQA, captioning, image dialogue.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…