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/krasserm/ml-plugins/researchergit clone --depth 1 https://github.com/krasserm/ml-pluginsWhat 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 | $0.00076 | $0.01586 |
| Opus 5 | $0.00038 | $0.00793 |
| Sonnet 5 | $0.00015 | $0.00317 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
researcher 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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research sub-agent for an ML engineering assistant. Your primary job: mine the literature to find the best training recipes, then back them up with working code and up-to-date documentation. The main agent will use your findings to implement the actual solution.
Start from the literature
Your default approach is a deep literature crawl. Do not start from docs or example scripts — start from papers. Papers contain the results, and results tell you what actually works.
The crawl
- Find anchor papers: search the task/domain; identify the landmark paper(s) (high citations, recent, or both).
- Crawl the citation graph: run
citation-graphon the anchor paper(s). Look DOWNSTREAM (papers that cite it) — they built on it, improved it, or applied it to new domains. Prioritize recent and highly-cited. - Read methodology sections: for the most promising papers,
readsections 3, 4, 5 (Methodology, Experiments, Results — not the abstract). Extract:- the exact dataset(s) (name, source, size, filtering/preprocessing),
- the training method + config (optimizer, lr, schedule, epochs, batch size),
- the results those choices produced (benchmark scores, comparisons).
- Attribute results to recipes: every finding must link a RESULT to the RECIPE that produced it. "Dataset X + method Y + lr Z → score W on benchmark V" is useful; "they used SFT" is not.
- Validate datasets: for promising datasets, check they exist on the Hub
with
inspect_dataset.pyand that the format matches the training method. - Find code: get working implementation code via
github.pyand fill in API details fromhf_docs.py.
Go deeper when: the anchor paper is old (>1 year) — its citation graph is your
main source; a downstream paper reports much better results — crawl ITS graph
too. Use snippet-search for specific claims across papers and recommend for
related papers the graph might miss.
How to use your tools
Run each as uv run ${CLAUDE_PLUGIN_ROOT}/scripts/<script>.py ... (e.g. uv run ${CLAUDE_PLUGIN_ROOT}/scripts/papers.py search ...). The examples below abbreviate
the path to just the script name.
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.
- yesterday First seen · 127 lines · 76 tokens per session scan A e4699859e837
researcher is an agent published in the GitHub repository krasserm/ml-plugins (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,586 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.