What is codex-panel-reproduce?

A workflow for recreating one scientific chart or figure panel as editable Python code using Matplotlib. It covers turning a supplied image into a script and rendered PNG and PDF files, with optional source information.

Use it to reproduce or refine a single panel from a scientific paper, presentation, or other figure as code and exported image files.

It helps make a figure editable and reproducible instead of leaving it as a fixed image. The workflow also defines how to review and refine the generated result.

codex-panel-reproduce — Skill by littlepeachs/NaturePanelForge

Install

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.

Any agent

npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce

Clone the repo

git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/littlepeachs/naturepanelforge/codex-panel-reproduce/github.svg)](https://agentmods.dev/skills/littlepeachs/naturepanelforge/codex-panel-reproduce)

Your own site

<a href="https://agentmods.dev/skills/littlepeachs/naturepanelforge/codex-panel-reproduce"><img src="https://agentmods.dev/badge/skills/littlepeachs/naturepanelforge/codex-panel-reproduce/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/littlepeachs/naturepanelforge/codex-panel-reproduce"><img src="https://agentmods.dev/badge/skills/littlepeachs/naturepanelforge/codex-panel-reproduce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00056	$0.01141
Opus 5.5	$0.00022	$0.00456
Sonnet 5.5	$0.00011	$0.00228
Haiku 4.5	$0.00006	$0.00114

Measured 2mo ago against content hash 08606a6473b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-panel-reproduce 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 2mo 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.

skills/codex-panel-reproduce/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Panel Reproduce

Trigger

Use this for code-only reproduction or refinement of one scientific figure panel in NaturePanelForge. The target is an editable Python script plus rendered PNG/PDF, not image editing or raster tracing.

For local user-supplied images, do not run Qwen scoring and do not require Qwen outputs. Qwen context is only optional metadata when the input already comes from an existing SciFigureHub/NaturePanelForge pipeline directory.

Inputs

Single-image workflow: a target panel image path, optional caption, optional source PDF.
Existing-panel workflow: a panel directory containing target.png; optional metadata.json, qwen_score.json, qwen_prompt.md, and raw_response.txt. Missing Qwen files are acceptable for user-supplied images.
Refine workflow: an existing panel directory containing target.png, reproduce_panel.py, reproduce_panel.png, and reproduce_panel.pdf.

Reproduce One Panel

Run from the NaturePanelForge repo root:

python3 forge.py single-panel-image \
  --image path/to/target_panel.png \
  --out-root UserRuns/single_panel \
  --panel-id my_panel \
  --caption "brief visual/caption context" \
  --chart-type user_supplied \
  --review-rounds 4 \
  --skip-existing

This command prepares the local single-image bundle itself. It writes placeholder user-image metadata as needed; it does not classify the image with Qwen and does not need a local Qwen model.

For an existing panel directory:

python3 examples/prompt_codex_reproduce_fig02_g.py \
  --panel-dir path/to/panel_dir \
  --panel-root path/to/panel_root \
  --reviews-dir path/to/reviews_root \
  --specs-dir path/to/specs_root \
  --jobs 1 \
  --review-rounds 4 \
  --skip-existing

Expected panel outputs:

reproduce_panel.py
reproduce_panel.png
reproduce_panel.pdf

Expected mirrored review/spec outputs:

reproduce_panel_run_log.md
reproduce_panel_review_notes.md
reproduce_panel_review_summary.json
reproduce_panel_prompt.md
reproduce_panel_raw_response.txt

Read the full file on GitHub · 121 lines

Changes

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.

2mo ago First seen · 121 lines · 56 tokens per session scan A 08606a6473b9

Subscribe to this mod's changes

codex-panel-reproduce is a skill published in the GitHub repository littlepeachs/NaturePanelForge (225 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,141 once invoked, about $0.0002 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 2026-08-30.

Languages Python Scientific

codex-panel-reproduce next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-panel-reproducelittlepeachs/NaturePanelForge	Skill	225	3mo ago	MIT	A	56	Claude Code, Codex
jupyter-notebookNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	18	Claude Code, Codex
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
pennylaneK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	74	Claude Code
cuequivariance-jaxNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	38	Claude Code, Codex
cuequivariance-torchNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	37	Claude Code, Codex
cuopt-numerical-optimization-apiNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	51	Claude Code, Codex