Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2npx agentmods add skills/ertinox7711/sgrr-agi-v2/engineering-figureWrote 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/ertinox7711/sgrr-agi-v2/engineering-figure)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/engineering-figure"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/engineering-figure/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/ertinox7711/sgrr-agi-v2/engineering-figure"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/engineering-figure.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 | $0.00092 | $0.03962 |
| Opus 5.5 | $0.00037 | $0.01585 |
| Sonnet 5.5 | $0.00018 | $0.00792 |
| Haiku 4.5 | $0.00009 | $0.00396 |
Grade A, and why
engineering-figure-agent 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 1mo 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Figure Agent
Overview
This skill adapts the Nano Banana or Gemini image workflow to computer science, electronics, algorithms, and engineering-paper figures.
Boundary / Handoff
Use this skill for the figure-production layer after the figure goal is already reasonably clear.
- Good fit: turn a figure brief into a conceptual diagram, engineering schematic, workflow figure, or exact publication plot.
- Good fit: choose between
imagemode andplotmode, build prompts, render plots, and apply figure-language, layout, color, and export constraints. - Not the main tool for: deciding from scratch what claim the paper should visualize, auditing whether a figure really supports the argument, or writing a full reviewer-style figure critique.
- If the user is still asking what figure they should make, what panels should exist, what claim each panel supports, or how the figure should be explained in the paper, hand off upstream to
ai-research-writing-guidefirst. - Recommended input from that upstream handoff:
figure goal,figure type,panel plan or module list,must-keep terms,caption or message,paper language, andvisual style constraints.
It should be treated as a provider-neutral workflow for image-generation backends:
- keep the official Google Gemini endpoint as the Banana/Gemini reference setup
- allow OpenAI Image API as a first-class image backend for conceptual figures and image edits
- allow third-party Gemini-compatible relays only when the user intentionally chooses them
- expect model names, auth mode, image-size options, and high-resolution options to vary by provider
Use two modes:
imagemode Use Gemini-compatible image generation or editing for conceptual figures, architecture diagrams, workflow schematics, graphical abstracts, and style-matched redraws.plotmode Use the bundled Python plotting tool for exact publication-style bar charts, trend curves, heatmaps, scatter plots, and multi-panel quantitative figures.
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.
- 1mo ago First seen · 343 lines · 92 tokens per session scan A ff629af9cbb8
engineering-figure-agent is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 3,962 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
proof-orchestrator
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or…
Science
The scientific method as a universal problem-solving algorithm — goal-first, plural falsifiable hypotheses, designed experiments, and honest measurement, scaling from TDD to feature validation to MVP launch. USE WHEN think about, figure out, experiment, iterate, optimize, hypothesis, science, full cycle, quick…
neqsim-setup
Configure and verify the NeqSim task environment: task root, document root, Word report template, and health of Java, the NeqSim JAR, the MCP server and the neqsim CLI. USE WHEN: a user runs /neqsim-setup, asks to set or show the task/document folder, work path or report template, asks 'is my NeqSim setup working'…
model-inference-optimize
A method for measuring and improving the speed, memory use, quality, and serving cost of machine-learning model inference. It covers workloads such as image, video, diffusion, and self-hosted language models while requiring experiments against a defined baseline.
monitor-experiment
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
health-nutrition-expert
Apply cutting-edge 2025 nutrition science on longevity, metabolic health, gut microbiome, and evidence-based dietary patterns for optimal vitality and disease prevention. Use when planning a diet, evaluating a nutrition claim, or applying evidence-based guidance on longevity, metabolic, and gut health.