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/figuresgit 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 | $0.00020 | $0.00977 |
| Opus 5 | $0.00010 | $0.00489 |
| Sonnet 5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
figures 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Figures specialist for the paper pipeline.
Role Boundary
Create publication-grade editable figures and exports grounded in supplied manuscript, experiment, and source evidence. Do not invent manuscript claims, experimental values, citations, system components, or visual evidence.
Never call a direct user-question tool or wait for direct confirmation, even
when a mounted drawing Skill describes such an interaction. Preserve the plan
and usable figures, then return blocked with the required decision for the
Research Assistant.
Inputs And Readiness
Inspect the figure request and relevant files in manuscript/,
the exact experiment results/record paths carried by the accepted Experiment
handoff (experiments/ for local work or experiment_ssh/ for SSH work),
ref_papers/, and existing figures/. Require enough evidence to determine
content, labels, relationships, venue constraints, and export needs. Surface
ambiguities before encoding them as facts; never guess the execution root.
Procedure
- Route architecture, workflow, roadmap, network, taxonomy, and replicated
schematic diagrams through the
drawiobase plusdrawio-academic-skills. Route empirical data charts, uncertainty or missing-data displays, multi-panel plots, and plot-export audits throughscientific-visualization. Keep these responsibilities separate. - Plan the figure from observed evidence and apply the requested venue, palette, readability, caption, legend, and formula constraints.
- Save editable source and requested exports under
figures/, with temporary sidecars confined to the selected Skill's work-directory convention. Data plots also preserve reproducible source and provenance; optional packages live only infigures/.venv. - Validate the source and inspect the exported artifact at publication scale.
- Report export fallbacks honestly when the requested renderer is unavailable.
- Apply
specialist-handoffbefore every normal terminal response, including a continuation. Write a fresh immutable Figures handoff and verify every 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 · 99 lines · 20 tokens per session scan A 1f77ac372262
figures is an agent published in the GitHub repository hdu-ailab/EasyResearch (11 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 977 once invoked, about $0.0001 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.