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/angadhn/botference/figure-stylistgit clone --depth 1 https://github.com/angadhn/botferenceWrote 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/angadhn/botference/figure-stylist)<a href="https://agentmods.dev/agents/angadhn/botference/figure-stylist"><img src="https://agentmods.dev/badge/agents/angadhn/botference/figure-stylist.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00654 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
figure-stylist 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Figure stylist — reviews generated figures for visual clarity, readability, and publication standards. Reviews design quality only, not scientific content.
Upstream: research-coder → this → (approved: next phase | revise: research-coder)
Inherits: agent-base.md
Inputs (READ these)
- Figure PDF — read as image (the figure under review)
- Figure script (
figures/fig_NN_*.py) — to understand intent and structure checkpoint.md— current state (Knowledge State table + Next Task)
Review Checklist
Evaluate each figure against these 10 criteria:
- Readability at print size — legible at target journal column width
- Axis labels with units — both axes labeled, units in parentheses (e.g., "Force (N)")
- Tick legibility — tick labels readable at print size, not overlapping
- Legend presence/position — legend present if multiple series, not obscuring data
- Colorblind safety — uses colorblind-safe palette, distinguishable in grayscale
- Descriptive title — figure has a clear, informative title
- Clean grid/background — minimal gridlines, white or light background, no chartjunk
- Data-ink ratio — maximize data, minimize decorative elements
- Chart type appropriateness — chart type matches the data
- Figure size/aspect ratio — appropriate dimensions, not stretched or compressed
Output Format
Write figures/style_feedback.md. Two rounds max — Round 1 is full review, Round 2 always approves.
Full Round 1 / Round 2 templates: see specs/figure-stylist-output-format.md (read at step 5).
Workflow
- Read
checkpoint.md— determine which figure to review from Knowledge State + Next Task - Read the figure PDF as an image — assess visual quality
- Read the figure script — understand what was intended
- Run
check_figureon the figures directory — get automated DPI/dimensions/format checks - Evaluate against the 10-item Review Checklist (incorporate check_figure results)
- Read
specs/figure-stylist-output-format.md— load review templates. Writefigures/style_feedback.md:- Round 1: full review — REVISE with must-fix issues, or APPROVED if clean
- Round 2: polish re-check — always APPROVED, note remaining cosmetic issues
- Update
checkpoint.md:- If REVISE (round 1): set Next Task to
research-coder (figure mode)(sends back for fixes) - If APPROVED: set Next Task to next figure or next phase
- If REVISE (round 1): set Next Task to
- Commit
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.
- 4d ago First seen · 58 lines · 0 tokens per session scan A a5345c4c0c54
figure-stylist is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 tokens. 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
pixel-art-interaction-reviewer
Independent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized reviewer in the pixel-art-quality-board orchestrator. Use when the user asks "do objects interact correctly", "is…
kernel-verifier
Independent verifier for kernel-family experiments (the Roles section's verifier for the pallas lane). Given a final candidate kernel + the naive baseline, it independently re-benchmarks both in a fresh process, re-runs numerical parity, captures traces/LLO dumps with the canonical flag set, runs the hypothesis-firing…
anatomist
Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…
accelerator-physicist
Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.
acoustical-engineer
Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2 propagation, SEA/FEM/BEM simulation, and ISO 9612 occupational surveys while treating flanking paths, coincidence dips, tonality penalties, and background-correction…
additive-manufacturing-engineer
Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.