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 Dsadd4/AgentFigureGallery --skill agent-figure-gallerygit clone --depth 1 https://github.com/Dsadd4/AgentFigureGalleryWrote 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/dsadd4/agentfiguregallery/agent-figure-gallery)<a href="https://agentmods.dev/skills/dsadd4/agentfiguregallery/agent-figure-gallery"><img src="https://agentmods.dev/badge/skills/dsadd4/agentfiguregallery/agent-figure-gallery.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00557 |
| Opus 5 | $0.00018 | $0.00279 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
agent-figure-gallery 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Figure Gallery
Core Rule
Treat this skill as a lightweight controller. Do not load the full visual corpus into the skill. Use AGENT_FIGURE_GALLERY_ROOT or DRAWING_KB_ROOT to point at the external AgentFigureGallery knowledge base.
Key Files
- KB root:
AGENT_FIGURE_GALLERY_ROOT=/path/to/AgentFigureGallery - CLI:
agentfiguregalleryorpython -m agentfiguregallery.cli - Gallery server: backend command that serves the reference gallery on localhost
- Candidate index:
data/reference_candidate_index.json - Global preferences:
data/reference_global_preferences.json - Reference sessions:
outputs/reference_sessions/
Minimal Workflow
- Resolve the KB root:
export AGENT_FIGURE_GALLERY_ROOT=/path/to/AgentFigureGallery - Query before reading individual references:
agentfiguregallery query --task "<user task>" - Generate visible candidates:
agentfiguregallery gallery --plot-type <plot_type> --task "<user task>" --limit 50 --serve - Record human preferences:
agentfiguregallery prefer --session outputs/reference_sessions/<session_id> --like <ID> --reject <ID> --select <ID> - Export a selected bundle:
agentfiguregallery bundle --session outputs/reference_sessions/<session_id> --copy-scripts - Use the bundle before writing or revising plotting code.
Preference Semantics
like: useful for this task or plot type.reject: not useful for this task or plot type.select: use this candidate for the current agent action.global_like: generally useful across tasks.global_reject: hide from future sessions.
Local preferences must preserve plot_type. Global preferences are cross-task.
Validation
After changing the CLI, gallery, preference logic, or bundle export:
agentfiguregallery gallery --plot-type embedding_plot --limit 20 --serve
agentfiguregallery prefer --session outputs/reference_sessions/<session_id> --like E01 --select E02
agentfiguregallery bundle --session outputs/reference_sessions/<session_id>
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.
- 8d ago First seen · 66 lines · 36 tokens per session scan A 8be0dfeba256
agent-figure-gallery is a skill published in the GitHub repository Dsadd4/AgentFigureGallery (146 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 557 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 skills, from other repositories
figure-library
Build, review, search, select, and materialize immutable scientific-figure references from Local Published, FigureYa, bundled Open Figure Modules, frozen explicit-only Community, and explicitly trusted dynamic Providers.
figure-description
Write or improve FigureYa-style scientific-template requirement descriptions, biological use cases and concise data profiles as Markdown. Use when creating/updating an SFL template description or asking what research questions a figure can illustrate; not for ordinary template search, execution or paper-legend…
figure-organization
Organize R or Python figure-replication and adaptation scripts into readable, owner-editable workflows with Chinese navigation comments and traceable inputs and outputs. Use when creating or reorganizing code for a selected SFL template, not for browsing templates or restructuring an unrelated application.
figure-style
Check correctness, legibility and faithful visual reproduction of selected scientific figure templates in R or Python. Use when adapting plotting code or inspecting rendered output, not for browsing templates. Includes an optional matplotlib sidecar and R-specific guidance; does not install packages or execute code…
origin-plotting
A guide to using Origin, a scientific graphing and analysis application, through connected tools. It covers writing data, making charts, formatting them, and viewing the results.
svg-editor
Open and surgically edit SVG scientific figures in the SVG Editor MCP App. Use when the user wants to change text, colors, fonts, positions, legends, or panel letters in an existing SVG by hand, or by selecting elements and instructing the host assistant.