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 hdu-ailab/EasyResearch --skill autoresearchgit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWrote 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/hdu-ailab/easyresearch/autoresearch)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/autoresearch"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/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/hdu-ailab/easyresearch/autoresearch"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 19 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.01688 |
| Opus 5.5 | $0.00021 | $0.00675 |
| Sonnet 5.5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
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 15d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch
Purpose
Turn one explicit user authorization into a sustained, metric-driven research campaign. Auto means the campaign keeps making valid experimental progress without asking for routine approval after every trial. It does not mean unbounded cost, unsafe mutation, metric hacking, or bypassing formal evidence requirements.
Follow the session's selected execution mode. In subagent-driven mode, Research
Assistant defines and monitors the campaign and one Experiment specialist owns
the trials. In single-Agent mode, Research Assistant applies the experiment
Skill and executes the same bounded loop directly, without child dispatch or a
specialist handoff. The campaign contract and evidence requirements apply in both.
Activation Contract
Treat an explicit auto/autoresearch/overnight/until-stopped request as approval for one exploratory campaign within an inspectable contract. Derive values from the user's request and existing project artifacts before asking anything.
The contract must name:
| Field | Requirement |
|---|---|
| Objective | One measurable experimental question |
| Selection metric | Primary validation metric and maximize/minimize direction |
| Evaluation boundary | Immutable evaluator, split, preprocessing, and anti-leakage rules |
| Mutable scope | Exact files or directories the Experiment specialist may change |
| Immutable scope | Evaluation harness, final-test data, source evidence, and protected files |
| Trial command | Reproducible command plus per-trial timeout |
| Budget | Trial count, wall-clock/compute budget, or explicit until-stopped authorization |
| Acceptance rule | Improvement threshold and simplicity/resource tie-breaker |
| Recovery | Snapshot and rollback method limited to mutable scope |
| Artifacts | Exact campaign, ledger, log, output, and summary paths |
Ask at most one focused question only when a safety-, cost-, or decision-critical field cannot be derived. Never invent a metric or silently authorize open-ended paid compute. An explicit until-stopped request is valid only on compute the user has already authorized.
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.
- 15d ago Changed · -20 lines 7d9a1bb28c94
- 1mo ago Changed · +25 lines 25b7a75eedf1
- 1mo ago First seen · 176 lines · 53 tokens per session scan A d333d9e53f5f
autoresearch is a skill published in the GitHub repository hdu-ailab/EasyResearch (14 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,688 once invoked, about $0.0002 per session on Opus 5.5. 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
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
alterlab-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…
alterlab-deep-research
Runs a 13-agent deep research pipeline for rigorous academic work on any topic across 7 modes (full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis), covering research-question formulation, Socratic mentoring, methodology…
alterlab-imaging-data-commons
Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for…
alterlab-pyhealth
Develops, tests, and validates clinical machine learning models with the PyHealth 2.x healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, length of stay, drug recommendation), medical coding systems (ICD, NDC, ATC, CCS), physiological signals…
alterlab-citation-verifier
Verifies that every bibliography entry actually exists by cross-checking Crossref, OpenAlex, Semantic Scholar, and arXiv (no API key required) plus doi.org DOI registration, fuzzy-matching title and authors (difflib ratio >= 0.70), flagging retractions recorded by Crossref (including Retraction Watch data) or…