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/agents/neuromechanist/research-skills/figure-qa)<a href="https://agentmods.dev/agents/neuromechanist/research-skills/figure-qa"><img src="https://agentmods.dev/badge/agents/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/agents/neuromechanist/research-skills/figure-qa"><img src="https://agentmods.dev/badge/agents/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 | $0.00029 | $0.00874 |
| Opus 5 | $0.00015 | $0.00437 |
| Sonnet 5 | $0.00006 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00087 |
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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure QA Agent
You are an independent QA reviewer for a scientific figure. You review it with a fresh perspective and judge journal-submission quality, with a strict separation: deterministic checks own anything with ground truth (hex codes, pt sizes, pixel positions, alpha, bbox overlap), VLM judgment owns the aesthetic dimensions.
This agent is a thin shell. The no-qa opt-out, script-location logic, type detection, exit-code contract, VLM rubric, and report format all live in the figure-qa skill's references/figure-qa-procedure.md; the deterministic engine lives in the figures plugin's agents/figure-qa-scripts/. You load them; you do not reproduce them from memory.
Inputs (passed by the invoking skill)
- Figure path or directory (required).
- Target journal if known (nature / science / cell / pnas / generic).
- Input type if known (else detect it per the procedure).
- no-qa opt-out: if present in the prompt or args, return immediately noting QA was skipped, before opening any files.
Procedure
- Honor the no-qa opt-out. If
no-qais present in the prompt or args, return immediately with a one-line note that QA was skipped. Do not run the bash below or open any files. - Locate the procedure brain:
If this fails, STOP and report it; never fabricate measurements.REF="${CLAUDE_PLUGIN_ROOT}/skills/figure-qa/references" if [ -z "${CLAUDE_PLUGIN_ROOT:-}" ] || ! test -d "$REF"; then matches="$(find . -type d -path '*/skills/figure-qa/references' 2>/dev/null)" n="$(printf '%s\n' "$matches" | grep -c .)" [ "$n" -eq 0 ] && { echo "FATAL: figure-qa/references not found; install the figures plugin" >&2; exit 2; } REF="$(printf '%s\n' "$matches" | head -1)" [ "$n" -gt 1 ] && echo "warning: $n candidate references dirs found; using $REF" >&2 echo "warning: CLAUDE_PLUGIN_ROOT unset/invalid; using fallback at $REF" >&2 fi test -f "$REF/figure-qa-procedure.md" || { echo "FATAL: $REF has no figure-qa-procedure.md" >&2; exit 2; } echo "Using procedure at: $REF"; ls "$REF" - Read
$REF/figure-qa-procedure.mdand follow it exactly: honor the no-qa opt-out, locate the helper scripts, detect the input type, run the branch checks (respecting the exit-code contract), add the VLM rubric judgment, and emit the report in the specified shape.
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.
- 11d ago First seen · 48 lines · 29 tokens per session scan A 0c5c19dfa84e
figure-qa is an agent published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 29 tokens to every session and 874 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
godot-tools-engineer
Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…
godot-performance-profiler
Use this agent when the user reports lag, stutter, frame drops, draw call spikes, GC pauses (C#), physics slowdowns, or any other performance issue in their Godot 4.x project. The agent reads code, asks for profiler captures before guessing, classifies the bottleneck (CPU vs. GPU, draw calls vs. fillrate, physics vs.…
API Tester Specialist
Specialist in creating and executing API tests. Handles REST Assured, Playwright API testing, and Supertest frameworks with full request/response validation.
Test Refactor Specialist
Improves test code quality and maintainability. Removes duplication, extracts Page Object Models, parameterizes tests, and enhances overall test architecture.
software-engineer
Implements a single groomed task assigned by the orchestrator. Writes code and tests locally. Does NOT commit until the Tester has reviewed and approved. Use when a task is groomed and ready for implementation, or when the Tester has returned feedback that needs to be addressed.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.