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 remote-experiment-preflightgit 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/remote-experiment-preflight)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/remote-experiment-preflight"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/remote-experiment-preflight/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/remote-experiment-preflight"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/remote-experiment-preflight.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 | $0.00034 | $0.01812 |
| Opus 5 | $0.00017 | $0.00906 |
| Sonnet 5 | $0.00007 | $0.00362 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade B, and why
remote-experiment-preflight scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- never install SSHFS or run a package manager/sudo automatically. How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Experiment Preflight
Boundary
This is the Research Assistant's narrow infrastructure exception. Configure and test one SSH server, inspect its compute, and establish a user-authorized mount. Do not write experiment code, install experiment dependencies, launch trials, or interpret results.
The first version supports exactly one server per project through
easyresearch.ssh. Do not create profile names, a server list, selection logic,
or compatibility fields for future multi-server support.
Required Values
Derive these from the conversation or ask one focused question for missing values:
- host or IP address;
- port;
- username;
- expected SSH host fingerprint in OpenSSH
SHA256:<base64>form, obtained from the server owner or another trusted channel; - authentication type:
passwordorprivate-key; - absolute credential-file path outside the paper project;
- optional absolute passphrase-file path for an encrypted private key;
- paper or project name, unless the user supplied an absolute POSIX remote project path;
- expected compute class and mount authority.
The credential file is user-managed. For password, its first line is the
password. For private-key, it contains the OpenSSH private key. File contents
must never be read with Agent-visible tools, copied into chat, written to
settings/artifacts, or included in diagnostics. Only paths may enter the
conversation and project settings.
Workspace Mapping
The local SSH experiment root is always the absolute
<exact-cwd>/experiment_ssh/. Do not ask the user to choose another local path
and do not mount an SSH workspace over local-only experiments/.
Select the remote project root in this order:
- Use an absolute POSIX path when the user explicitly supplied one.
- Otherwise derive a short project name from the approved paper title, project name, existing project artifacts, or exact-cwd basename, in that order.
- Convert that name to one lowercase conservative ASCII slug: translate a
non-ASCII title to a concise meaningful English name when needed, replace
each run outside
a-z,0-9,.,_, and-with one-, collapse repeated-, and trim punctuation from both ends. If no non-empty meaningful slug remains, ask for the project name, not a server path. - Configure the home-relative remote root as
<slug>/, which means$HOME/<slug>/for creation, commands, and SSHFS.
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 · 186 lines · 34 tokens per session scan B fb74d566ba06
remote-experiment-preflight is a skill published in the GitHub repository hdu-ailab/EasyResearch (13 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,812 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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…
ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of currentresearch with auditable repo…
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with…
env-and-assets-bootstrap
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full…
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or…
safe-debug
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research…