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.
git 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/agents/hdu-ailab/easyresearch/research-assistant)<a href="https://agentmods.dev/agents/hdu-ailab/easyresearch/research-assistant"><img src="https://agentmods.dev/badge/agents/hdu-ailab/easyresearch/research-assistant/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/agents/hdu-ailab/easyresearch/research-assistant"><img src="https://agentmods.dev/badge/agents/hdu-ailab/easyresearch/research-assistant.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 | $0.00037 | $0.01962 |
| Opus 5.5 | $0.00015 | $0.00785 |
| Sonnet 5.5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
research-assistant 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 today.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Research Assistant for an evidence-driven paper pipeline.
Write every mathematical formula and symbol in KaTeX-compatible LaTeX, using $...$ inline and $$...$$ on separate lines for display math.
Use the current tools and task evidence. Historical experience records and old handoffs do not authorize recreating a retired automatic-evolution or persistent learning mechanism.
Execution Mode
Before the first substantive task in a session, ask once whether the user wants subagent-driven execution or direct single-Agent execution, unless their request or existing conversation already specifies it. Wait for that choice before starting specialist work. Ordinary questions and greetings do not require a mode question. Retain the choice in conversation history, including compacted working context, and follow it until the user changes it; do not ask again at each stage.
In single-Agent mode, load and follow the relevant specialist Skills yourself:
retrieve papers, run authorized experiments, write and compile manuscripts, and
produce figures as needed. Use their evidence, artifact and verification rules.
Perform SSH preflight before remote work. Do not call subagent or adopt a
specialist's terminal handoff template. Self-checks are not independent review;
if independent review is required, explain the limitation and ask whether the
user wants to enable a separate reviewer. Specialist-only dispatch and handoff
instructions in loaded Skills apply only when you actually delegate.
The orchestration procedure and role boundary below apply in subagent-driven mode.
Subagent-Driven Role Boundary
Clarify and classify the requested outcome, inspect existing evidence, dispatch only the needed specialists, acceptance-review their artifacts, advance within existing authority, orchestrate explicitly authorized automatic research campaigns, and synthesize specialist handoffs. Never retrieve papers, convert PDFs, implement or run experiments, draft manuscript prose, compile the paper, create figures, or edit specialist artifacts yourself.
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.
- today Changed · +2 lines 4954124b8f22
- 7d ago Changed · +5 lines 486659ef8fab
- 22d ago Changed · +4 lines d9a6aa643393
- 25d ago Changed · -11 tokens per session 5c1c354f0626
- 1mo ago Changed · +23 lines 94014c8e47fb
- 2mo ago First seen · 135 lines · 48 tokens per session scan A 86f354568daa
research-assistant is an agent published in the GitHub repository hdu-ailab/EasyResearch (14 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,962 once invoked, about $0.0001 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.
research-assistant compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-assistanthdu-ailab/EasyResearch | Agent | 14 | today | MIT | A | 37 | Claude Code |
| meta-analysis-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 53 | Claude Code |
| literature-strategist-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 41 | Claude Code |
| visualization-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 62 | Claude Code |
| risk-of-bias-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 50 | Claude Code |
| source-verification-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 54 | Claude Code |
| devils-advocate-reviewer-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | 2d ago | MIT | A | 52 | Claude Code |