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 instructions/xuzhougeng/svg-editor/agents-mdgit clone --depth 1 https://github.com/xuzhougeng/svg-editorWhat 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 | $0.00231 | $0.00231 |
| Opus 5 | $0.00115 | $0.00115 |
| Sonnet 5 | $0.00046 | $0.00046 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
svg-editor AGENTS.md 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 today.
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.
What it actually says
SVG Editor
MCP App plugin for Wisp Science and Claude Science. Users edit SVG figures by clicking or by natural-language / spoken instructions in the host chat.
GitHub README is English-first (README.md) for search; Chinese copy is README.zh-CN.md.
Layout
src/server/— stdio MCP server, SVG DOM ops, sanitizesrc/ui/— sandboxed MCP App editorsrc/shared/— types and local command grammarskills/svg-editor/SKILL.md— agent instructions.claude-plugin/plugin.json+.mcp.json— Claude / Wisp plugin manifest
Commands
npm install
npm test
npm run build
npm run build writes dist/, dist-plugin/, svg-editor-for-claude-science.zip.
Install the zip in Wisp Settings → Plugins or Claude Science / Claude Code --plugin-dir.
Do not regenerate whole SVGs in agent tools. Use svg_inspect + svg_apply.
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.
- today First seen · 28 lines · 231 tokens per session scan A 7bd52b34f2e8
svg-editor AGENTS.md is an instructions file published in the GitHub repository xuzhougeng/svg-editor (0 stars, last pushed 6d ago), licensed MIT. It adds 231 tokens to every session, about $0.0012 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 instructions, from other repositories
motif AGENTS.md
Instructions for jvogan/motif, covering motif for claude science — agent guide, start here, important paths, product contracts and guardrails.
open-science AGENTS.md
AGENTS.md instructions for ai4s-research/open-science, covering open science desktop, design principles, what this project is, repository map and architecture guardrails.
claude-science-api-bridge AGENTS.md
Instructions for Jyx0208/claude-science-api-bridge, covering agent operating manual, prime directive, goal, repository map and success criteria.
superset copilot-instructions.md
Instructions for apache/superset, a project described as: Apache Superset is a Data Visualization and Data Exploration Platform.
superset CLAUDE.md
Instructions for apache/superset, a project described as: Apache Superset is a Data Visualization and Data Exploration Platform.
superset GEMINI.md
Instructions for apache/superset, a project described as: Apache Superset is a Data Visualization and Data Exploration Platform.