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 yzhao062/anywhere-agents --skill editable-figuregit clone --depth 1 https://github.com/yzhao062/anywhere-agentsWrote 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/yzhao062/anywhere-agents/editable-figure)<a href="https://agentmods.dev/skills/yzhao062/anywhere-agents/editable-figure"><img src="https://agentmods.dev/badge/skills/yzhao062/anywhere-agents/editable-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/yzhao062/anywhere-agents/editable-figure"><img src="https://agentmods.dev/badge/skills/yzhao062/anywhere-agents/editable-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 | $0.00152 | $0.05336 |
| Opus 5.5 | $0.00061 | $0.02134 |
| Sonnet 5.5 | $0.00030 | $0.01067 |
| Haiku 4.5 | $0.00015 | $0.00534 |
Grade A, and why
editable-figure 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 19d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editable Figure
Overview
The author's primary use is the overview or Figure 1 in paper and proposal writing. Prioritize visual narrative, composition, concrete domain objects, and information hierarchy. Standalone data-analysis charts belong to a plotting workflow such as Matplotlib; a result inset may support an overview when it helps its argument.
Turn a document's central idea into a figure that a reader can understand quickly, then deliver a PowerPoint source that the author can actually edit. For a new overview or substantial redesign, first analyze the source, study references, and design the takeaway. Then generate two independent visual concepts, select and combine, build editable layers, and inspect in context. Use existing authorization for both generators; otherwise propose that step before dispatch. Small revisions can reuse the accepted composition. Paper, proposal, and README figures share these principles but serve different reader decisions.
Top design priority: understand and imitate the author's preferences
For Yue Zhao's paper and proposal figures, follow the required preference-first design protocol before choosing a composition or generating a draft. Read the latest feedback, inspect the relevant reference images, and state which confirmed qualities will be imitated and how. Apply that mapping in every generator brief and in the implementation, then compare the output against the selected images before delivery. Merely mentioning the gallery is insufficient. This priority outranks generic palette, minimalism, icon, and text-density defaults; current task instructions, scientific correctness, and required deliverable constraints remain binding. Other users must confirm their own preferences.
Choose the scope
Respect the requested deliverable. An assessment or prompt-only request does not require generating a deck. Once figure creation is authorized, use subsequent feedback to revise the artifact without repeatedly asking permission. Choose a reasonable composition and produce a reviewable draft when the source is sufficient.
What ships with it
44 files 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.
- agents/openai.yaml 636 B
- references/default-palette.json 414 B
- references/default-palette.md 6.0 KB
- references/document-contexts.md 4.8 KB
- references/gallery/01-nsf-fire/main_figure.pdf 964 KB
- references/gallery/01-nsf-fire/preview.png 3104 KB
- references/gallery/02-openlibsignal-ecosystem/ecosystem-pic-all.pdf 4476 KB
- references/gallery/02-openlibsignal-ecosystem/preview.png 1264 KB
- references/gallery/03-openlibsignal-framework/plot.pdf 421 KB
- references/gallery/03-openlibsignal-framework/preview.png 666 KB
- references/gallery/04-catchbench/CatchBench-figure1.pdf 133 KB
- references/gallery/04-catchbench/preview.png 153 KB
- references/gallery/05-cat-dpo/method_overview.pdf 248 KB
- references/gallery/05-cat-dpo/preview.png 260 KB
- references/gallery/06-no-attacker-needed-example/fig_intro.png 139 KB
- references/gallery/07-no-attacker-needed-architecture/fig_main.png 137 KB
- references/gallery/08-spatial-reasoning/overview.pdf 35 KB
- references/gallery/08-spatial-reasoning/preview.png 252 KB
- references/gallery/09-memory-retrieval/demo2.png 131 KB
- references/gallery/10-dora-geographic-coverage/codex-clipboard-f42ec793-21bc-4ff8-9f38-78f397506ddd.png 433 KB
- references/gallery/11-dora-annotation-pipeline/codex-clipboard-b763a1a1-4023-4421-8d3a-d8e91a8fc901.png 315 KB
- references/gallery/12-tdc-overview/codex-clipboard-e0258486-34b8-420e-9a33-5fb1e7b8944e.png 678 KB
- references/gallery/13-metaood-overview/codex-clipboard-0e32ef07-495a-4370-8a0f-ed07519a1138.png 202 KB
- references/gallery/14-memoharness-overview/codex-clipboard-d3e30e78-9e05-447f-83d7-a8900e6e6365.png 520 KB
- references/gallery/15-fedgnn-attacks/codex-clipboard-f55c8780-b566-4240-9822-09595e17b676.png 393 KB
- references/gallery/gallery-9-figures.html 216 B
- references/gallery/index.html 17 KB
- references/gallery/index.md 18 KB
- references/gallery/preferences.md 9.8 KB
- references/gallery/sources.json 15 KB
- references/hybrid-figures.md 10 KB
- references/iteration-example.md 5.3 KB
- references/mechanism-figures.md 6.0 KB
- references/native-powerpoint.md 18 KB
- references/panels-and-results.md 6.6 KB
- references/paper-first-figures.md 5.4 KB
- references/position-and-concept-figures.md 5.3 KB
- references/proposal-figures.md 12 KB
- references/proposal-style-exemplars.md 7.8 KB
- references/reference-search.md 11 KB
- references/space-efficiency.md 3.7 KB
- scripts/build_gallery.py 6.6 KB runs code
- scripts/inspect_figure_pdf.py 4.2 KB runs code
- scripts/render_powerpoint.ps1 5.2 KB runs code
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.
- 19d ago Changed · +10 lines · +9 tokens per session 10c106cb8be2
- 20d ago Changed · +4 lines 8dcb387d7984
- 24d ago Changed · +6 lines · +18 tokens per session b07258661eb4
- 1mo ago Changed · +6 lines 742f0b96f41d
- 1mo ago First seen · 158 lines · 125 tokens per session scan A 10ce5c2ba466
editable-figure is a skill published in the GitHub repository yzhao062/anywhere-agents (257 stars, last pushed 2d ago), licensed Apache-2.0. It adds 152 tokens to every session and 5,336 once invoked, about $0.0006 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 2026-09-07.
Other skills, from other repositories
detecting-dependency-confusion
Detect and prevent public-over-private name resolution in npm, PyPI, and Maven.
detecting-typosquatting-packages-in-npm-pypi
Detects typosquatting attacks in npm and PyPI package registries by analyzing package name similarity using Levenshtein distance and other string metrics, examining publish date heuristics to identify recently created packages mimicking established ones, and flagging download count anomalies where suspicious packages…
detecting-typosquatting-packages
Flag misspelled, brandjacked, and typosquatted package names across npm, PyPI, and crates.io before installation using edit-distance, keyboard-proximity, and known-target corpus matching with typomania, OSSGadget, and pypi-scan.
desktop-visual-design
Use when building or styling desktop apps, Quickshell QML components, bars, panels, popups, launchers, notifications, or widgets that should fit an existing system theme. Derives reusable palette, interaction, spacing, typography, border, geometry, and motion tokens from the target project and desktop instead of…
frontend-design
Use when building, redesigning, or fixing a web interface. Combines distinctive visual direction with expected interaction behavior, accessible controls, complete user flows, failure recovery, and verification. Infer ordinary usability requirements without inventing product features.
micrographic
Use this skill to build micrographic UI components and views — cards, panels, dashboards, dense data displays — matching the industrial label collage north star (examples/reference-collage.png). Compression not minimalism; metadata as texture. Two type scales (display 80px+ vs micro 7–11px); dual display modes (light…