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 agentmods add skills/cliffren/swf/fignpx skills add cliffren/swf --skill figgit clone --depth 1 https://github.com/cliffren/swfWhat 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 | $0.00025 | $0.01945 |
| Opus 5 | $0.00013 | $0.00972 |
| Sonnet 5 | $0.00005 | $0.00389 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
fig 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 2d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure Management
Create, iterate, and organize publication-quality figures for papers.
Sub-commands
$ARGUMENTS[0] determines the action. If omitted, show help.
/swf:fig framework <description>
Create a framework/architecture diagram (typically Fig.1 of a paper).
-
Choose tool based on need:
- draw.io MCP — default choice. Best for flowcharts, pipelines, architecture diagrams. Claude has full control: create, edit, export.
- Figma MCP — use when the user asks, or when working with existing Figma designs. Best for polished visual design and FigJam collaboration.
-
Ask the user: "用 draw.io 还是 Figma 画?"
- If user has no preference, default to draw.io (Claude has more control)
-
draw.io workflow:
- Call
start_sessionto open browser preview - Ask the user to describe what the diagram should show
- Call
create_new_diagramwith well-structured XML:- Use large shapes (width >= 200, height >= 60)
- Center layout on canvas
- Use thick lines (strokeWidth >= 2)
- Use a consistent color palette
- Add proper spacing (150-200px between shapes)
- Iterate: user says what to change → call
edit_diagram - When satisfied, call
export_diagramto save:.drawio→ for further editing in draw.io desktop.svg→ for paper inclusion (vector, scalable).png→ for quick preview
- Save to
docs/paper/figures/
- Call
-
Figma workflow:
- Use
generate_diagramto create in FigJam - Or use
create_new_file+use_figmafor Figma design files - Use
get_screenshotto preview - Export from Figma UI
- Use
-
Record in experiment log:
- Note which figure this is for (e.g., Fig.1 — Method Overview)
- Record the source file path
/swf:fig plot <description>
Generate a data visualization figure from experiment results.
- Read experiment data:
- Check
results/for metrics files - Check
docs/experiments/for relevant experiment records - Identify what data to plot
- Check
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.
- 2d ago First seen · 216 lines · 25 tokens per session scan A 84d4ca881bc4
fig is a skill published in the GitHub repository cliffren/swf (5 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,945 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-cartesian
An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.
html-ppt-zhangzara-monochrome
A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
paper-poster-html
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper…