Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add neuromechanist/research-skills/plugin install figuresWrote 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-qa)<a href="https://agentmods.dev/skills/neuromechanist/research-skills/figure-qa"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/figure-qa/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-qa"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/figure-qa.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 | $0.00115 | $0.00822 |
| Opus 5 | $0.00057 | $0.00411 |
| Sonnet 5 | $0.00023 | $0.00164 |
| Haiku 4.5 | $0.00012 | $0.00082 |
Grade A, and why
figure-qa 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 12d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure QA
Routes a scientific figure to an independent, fresh-context QA reviewer that detects the input type, runs the deterministic checks (fonts, palette, geometry, alpha, DPI) via helper scripts, and adds a VLM rubric judgment for the aesthetic dimensions. This skill is a thin dispatcher: the detection logic, exit-code contract, VLM rubric, and report format all live in references/figure-qa-procedure.md, and the deterministic engine lives in the figures plugin's agents/figure-qa-scripts/.
When to use
Activate when a figure needs a journal-submission QA pass, or proactively after a figure-generation skill (scientific-figure, svg-figure, svg-primitives, transparent-icons, ai-full-figure, plot-styling) produces output, unless the caller passes no-qa.
Why a fresh-context reviewer
A QA pass is more trustworthy from a reviewer that did not just author the figure. Run it in a separate context and pass only the figure path, input type (if known), and target journal. On tools without subagents, run the procedure inline.
Dispatch
In every branch the reviewer follows references/figure-qa-procedure.md (strict separation: scripts own ground-truth measurements, VLM owns aesthetic judgment).
- Claude Code:
Task(subagent_type: "figure-qa", ...)passing the figure path and target journal. Honor ano-qaopt-out by returning immediately. - Codex CLI: plugin installation exposes this skill, not a Codex subagent. To use a fresh-context Codex reviewer, first copy
agents/templates/figure-qa.tomlto~/.codex/agents/or.codex/agents/, then invoke that configured agent if the current Codex surface supports/agent. If no Codex subagent is configured or available, use the fallback branch. - Copilot CLI: plugin installation exposes this skill and, through
.github/plugin/plugin.json, the.agent.mdreviewer inagents/templates/. Invoke that configured agent when the current Copilot surface supports custom agents. If running outside a plugin install, copyagents/templates/figure-qa.agent.mdto.github/agents/or~/.copilot/agents/. If no custom agent is available, use the fallback branch. - Fallback (no subagent support, or an interactive in-thread check): first locate the procedure (
$CLAUDE_PLUGIN_ROOT/skills/figure-qa/references, elsefind . -type d -path '*/skills/figure-qa/references' | head -1); if it cannot be found, stop and tell the user to install the figures plugin rather than guessing checks. Then followreferences/figure-qa-procedure.mddirectly.
What ships with it
1 file 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.
- 12d ago First seen · 32 lines · 115 tokens per session scan A 8dcf421dda7e
figure-qa is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 115 tokens to every session and 822 once invoked, about $0.0006 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
latex-posters
Use when creating or revising LaTeX research posters with beamerposter, tikzposter, or baposter, including poster layout, typography, color, print sizing, figure placement, QR codes, compilation, and print-ready PDF checks.
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
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…
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.
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…