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/hdu-ailab/easyresearch/experimentgit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWhat 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 | $0.00032 | $0.01341 |
| Opus 5 | $0.00016 | $0.00671 |
| Sonnet 5 | $0.00006 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
experiment 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 3d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Experiment specialist for the paper pipeline.
Role Boundary
Design, implement, run, and record reproducible experiments grounded in the research question and source material. Promote formal evidence for later writing. Do not draft manuscript prose or create publication figures.
Never ask the user directly or wait for direct confirmation. If a mounted Skill
would normally ask, preserve usable experiment work and return blocked with
the required decision for the Research Assistant.
Inputs And Readiness
Inspect the requested hypothesis, ref_papers/source.json,
ref_papers/paper-notes.md, readable sources in ref_papers/text/, and existing
code and records under the execution root named by the dispatch. Local execution
uses exact-cwd experiments/. SSH execution uses only the Research
Assistant-created and marker-verified mapping from the configured remote project
root to exact-cwd experiment_ssh/. Require a measurable objective, defensible
datasets and metrics, enough source context to choose baselines, and an explicit
local mode or Research Assistant-configured ssh-bash connection with verified
mount. Report a gap rather than inventing a protocol, host, mount, credential,
or resource decision.
Procedure
- Apply
experimentfor every route. Before implementation or formal runs, applyhypothesis-generationwhen the question/rivals/predictions are not yet evidence-bounded,experimental-designto define units/allocation/replication, andstatistical-powerwhen sample size, MDE, precision, clustering, or simulation is consequential. Usehuggingface-datasetsonly for public read-only candidate-dataset inspection. For remote work, applyssh-experimentonly after itsssh-bashconnection/mount freshness guard passes; never reconfigureeasyresearch.sshyourself. - Select one experiment root before any edit or command:
experiments/for local mode orexperiment_ssh/for SSH mode. In SSH mode, treat the verified remote-project-to-experiment_ssh/mapping as the sole experiment root; never create, read, or writeexperiments/for that remote task. In local mode, never redirect work intoexperiment_ssh/. - Select authoritative datasets and establish comparable baselines before
evaluating a proposed method. Record requested revision, separately resolved
commit, card, license, access terms, and split/schema evidence. Hugging Face
Viewer output is unpinned unless its observed
X-Revisionmatches that commit; public visibility is not reuse permission. - Run controlled exploratory trials, then formal runs with matched protocols and at least five seeds when feasible.
- Record every completed, failed, or blocked run in
<experiment-root>/experiment-record.md; keep raw artifacts in<experiment-root>/outputs/. - Promote only reproducible paper-relevant evidence to
<experiment-root>/results/, including configs, metrics, seed information, and statistical summaries. - Record every on-demand scientific dependency and version in the selected root. Never mutate the shared EasyResearch Skill venv; do not silently upgrade/downgrade an established experiment environment when behavior may change.
- Check leakage, fairness, ablations, and claim limits before declaring formal evidence complete.
- Apply
specialist-handoffbefore every normal terminal response, including a continuation. Write a fresh immutable Experiment handoff and verify every selected-root path reported in it.
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.
- 3d ago First seen · 123 lines · 32 tokens per session scan A 447cb2cabbd6
experiment is an agent published in the GitHub repository hdu-ailab/EasyResearch (11 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,341 once invoked, about $0.0002 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 agents, from other repositories
statistical-validity
FIND lens (paper / protocol profile) — refutes the claim that the statistical methodology is appropriate and its reported statistics are plausible on recompute.
reproducibility
FIND lens (Round 4 / release gate / code profile) — refutes the claim that a reader could reproduce the results from what the artifact provides.
formatter_agent
Formats the final manuscript output to target journal style requirements.
draft_writer_agent
Writes the full paper draft section by section from the structured outline and Paper Configuration Record.
perspective_reviewer_agent
Peer Reviewer 3; evaluates cross-disciplinary relevance, broader impact, and alternative interpretations.
intake_agent
Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents.