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 neuromechanist/research-skills --skill figure-biblegit clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/neuromechanist/research-skills/figure-bible)<a href="https://agentmods.dev/skills/neuromechanist/research-skills/figure-bible"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/figure-bible/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/neuromechanist/research-skills/figure-bible"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/figure-bible.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 | $0.00077 | $0.01124 |
| Opus 5.5 | $0.00031 | $0.00450 |
| Sonnet 5.5 | $0.00015 | $0.00225 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
figure-bible 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 25d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure Bible
Authors one figures/theme.json per project: the palette, typography, composition rules, and image-model preferences that every figure, icon, and plot should share.
This is step zero.
Run it before any generation skill produces output, not after.
When to use
- Starting a new paper, grant, or poster and no
figures/theme.jsonexists yet. - The user wants a consistent look across many figures (same colors, same font cue, same AI model settings).
- A generation or QA skill reports palette drift (
check_svg.py/check_raster.pyfindingpalette_off) and the project has no bible to point them at.
Skip it for a single one-off figure with no reuse; the generation skill's own defaults are fine there.
Scripts
Both scripts live in scripts/ (relative to this skill's base directory) and import the plugin's shared lib/theme.py by resolving their own path, so they work from a plugin install or a checkout.
Scaffold a theme:
uv run python scripts/init_theme.py --journal nature --out figures/theme.json \
--preset okabe-ito --font Helvetica \
--style "flat vector, minimal" --negative "gradients,shadows"
--journal is required: nature, science, cell, pnas, poster, or slide (drives the default page width and minimum text size).
--preset picks a starting palette: okabe-ito (default, colorblind-safe 8-color set), tol-bright, wong (alias of okabe-ito), or neuro-flat (navy/terracotta/cream plus three accents).
Override individual roles with --primary, --accent, --neutral (hex).
Add reference images for style transfer with repeated --reference img.png.
Set the image-model defaults with --codex-model and --codex-effort.
Re-running with --force overwrites an existing file; without it, the script refuses to clobber a theme someone already tuned.
Validate a theme (CI, pre-commit, or before trusting an edited theme.json):
uv run --with jsonschema python scripts/validate_theme.py figures/theme.json
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago First seen · 75 lines · 77 tokens per session scan A ed0dcf5b4525
figure-bible is a skill published in the GitHub repository neuromechanist/research-skills (48 stars, last pushed today), licensed BSD-3-Clause. It adds 77 tokens to every session and 1,124 once invoked, about $0.0003 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 2026-09-21.
Other skills, from other repositories
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
food-analyzer
Analyze food photos, nutrition labels, and ingredient lists. Trigger on food images, nutrition label scans, macro questions, glycemic questions, medication interaction checks, and similar food-analysis requests.
astrophotography-processing
Router for astrophotography processing, troubleshooting, and safe workflow guidance across deep-sky, narrowband, planetary/lunar/solar, Milky Way landscape, comet, and mosaic data.
photonforge-layout-verification
Assemble, route, inspect, and verify PhotonForge photonic layouts from schematic or netlist intent. Use when the user is working with componentfromnetlist, Reference placement, physical connections, virtual connections, pf.parametric.route, routing errors, port or terminal exposure, getnetlist, LVS-style checks…
scienceworld-measurement-taker
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting…
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.