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 gaasher/Agent-Loop-Skills --skill ml-autoresearchgit clone --depth 1 https://github.com/gaasher/Agent-Loop-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/gaasher/agent-loop-skills/ml-autoresearch)<a href="https://agentmods.dev/skills/gaasher/agent-loop-skills/ml-autoresearch"><img src="https://agentmods.dev/badge/skills/gaasher/agent-loop-skills/ml-autoresearch.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 121 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 91 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00118 | $0.05218 |
| Opus 5 | $0.00059 | $0.02609 |
| Sonnet 5 | $0.00024 | $0.01044 |
| Haiku 4.5 | $0.00012 | $0.00522 |
Grade A, and why
ml-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 8d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Autoresearch Loop
This loop is analysis-first: every experiment is followed by a diagnostic pass that examines what
happened inside the model, and the next change is a hypothesis grounded in that evidence — not a guess.
The feedback signal is <metric> read from the run log; the analysis is the spine that decides what to
change. A <literature> dial (on/off) optionally grounds each change in prior work via the sibling
literature-search skill. One change per iteration, so each metric move is attributable.
You are the researcher. Do not pause to ask for permission once the loop is running.
When to use
Use for an open-ended, autonomous ML research campaign where you want each change motivated by analysis
of the model's actual behaviour. Set <literature> = off for a self-contained analysis-and-score loop;
set <literature> = on to additionally ground changes in the scientific literature (paper search,
evidence grading, a reusable findings backlog). Not for a single training run, a fixed sweep, or tasks
with no measurable scalar metric. Default to off unless the user wants literature grounding or the
problem is a known, well-published one where prior recipes will pay off.
Setup
Resolve bindings interactively. If loop.run.yaml exists in the working dir, load it and skip to
the loop. Otherwise: on Claude Code (the AskUserQuestion tool is available — record <host> =
claude-code) infer a likely value for each binding from the project and present it as the recommended
option; on other hosts (<host> = other) ask each as a quoted plain-text prompt. Then write
loop.run.yaml (format: examples/run.example.yaml) and confirm every value with the user before
creating any other files. For branches strategy, create git checkout -b autoresearch/<run_tag>
(tag from today's date; branch must not exist). For time gating, write <sandbox_root>/run_with_timeout.sh
(timeout $(( <budget> * 60 )) <entrypoint> "$@") and use it as the run command, hard-killing at
2 × <budget> min; for epochs, patch the epoch cap in an <editable_files> file.
What ships with it
3 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.
- 8d ago First seen · 278 lines · 118 tokens per session scan A 294f14ed4724
ml-autoresearch is a skill published in the GitHub repository gaasher/Agent-Loop-Skills (164 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 5,218 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 skills, from other repositories
cerna-analysis
Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory. NOT for: differential expression, single-cell analysis, enrichment analysis, or workflows without a key gene…
cibersort-immune-infiltration-analysis
Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq…
gene-protein-expression-matrix-normalization
Use when normalizing bulk gene or protein expression matrices with log2 transform, z-score standardization, or min-max scaling before downstream visualization or exploratory analysis. NOT for count-model normalization such as TPM/DESeq2 size factors, batch correction, or single-cell preprocessing.
template-autoresearch-project
AutoResearch loop exemplar — deterministic ML candidate evaluation, evidence registries, claim ledgers, artifact manifests, readiness gates.
autoresearch-ml
Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures valbpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize valbpb"…
autoresearch-ml-skill
Autonomous ML training research loop (NVIDIA GPU required) — modify train.py, run fixed-budget experiment, parse valbpb, keep/revert. karpathy-style.