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 jamcgrath/svelte-component-graph-mcp --skill svelte-graphgit clone --depth 1 https://github.com/jamcgrath/svelte-component-graph-mcpWrote 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/jamcgrath/svelte-component-graph-mcp/svelte-graph)<a href="https://agentmods.dev/skills/jamcgrath/svelte-component-graph-mcp/svelte-graph"><img src="https://agentmods.dev/badge/skills/jamcgrath/svelte-component-graph-mcp/svelte-graph/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/jamcgrath/svelte-component-graph-mcp/svelte-graph"><img src="https://agentmods.dev/badge/skills/jamcgrath/svelte-component-graph-mcp/svelte-graph.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 | $0.00908 |
| Opus 5.5 | $0.00037 | $0.00363 |
| Sonnet 5.5 | $0.00018 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
svelte-graph 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte component graph
This skill drives the svelte-component-graph-mcp server, which parses a
Svelte/SvelteKit project into a component dependency graph. Prefer these tools
over manually grepping import statements — the parser already resolves
relative + $lib imports, <svelte:component this={Ident}>, and unused
imports, and it caches per file.
Prerequisite
The svelte-component-graph-mcp server must be configured in MCP settings.
If its tools aren't available, tell the user to add it (see the package README)
rather than falling back to grep.
Resolving root
Every tool needs root — an absolute path to the project being analyzed:
- If
svelte.config.jsexists in the current working directory,rootis the cwd ($PWD). - Otherwise (monorepo, or cwd is a subfolder), use the project's absolute path. If unsure which package, ask.
root must be absolute, exist, and contain at least one .svelte file — the
tools return an error otherwise.
The tools
| Tool | Use it to… |
|---|---|
get_graph(root) |
Get the whole map: every node (id, label, type, unused?) + every import link. Start here for "map the app" / broad impact analysis. |
get_component(root, path) |
Drill into one file. Returns parents (who imports it), children (what it imports), unused, isRoute, and its Svelte 5 props (name/optional/bindable/rest) + slots. path is workspace-relative (src/lib/Button.svelte). |
get_unused(root) |
List imported-but-never-rendered components (dead-code candidates). |
get_routes(root) |
Every +page/+layout/+error route with the components it directly pulls in. |
scan(root) |
Force a full re-parse (bypass caches) and return node/link counts. Use after large external changes (branch switch, generated files) when you want guaranteed-fresh results. |
Node ids are workspace-relative POSIX paths and are the source of truth for
lookups/links. Labels are display names (Button, (page) /dashboard).
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 · 73 lines · 92 tokens per session scan A d473a15ffce9
svelte-graph is a skill published in the GitHub repository jamcgrath/svelte-component-graph-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 908 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 2026-08-31.
svelte-graph compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| svelte-graphjamcgrath/svelte-component-graph-mcp | Skill | 0 | 4mo ago | MIT | A | 92 | Claude Code |
| shadcn-sveltevercel-labs/json-render | Skill | 19k | 2d ago | Apache-2.0 | A | 63 | Claude Code, Codex |
| add-localizationmicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 69 | Claude Code |
| vue-router-best-practicesvuejs-ai/skills | Skill | 3.3k | 16d ago | MIT | A | 25 | Claude Code, Codex |
| moai-domain-uiuxmodu-ai/moai-adk | Skill | 1.3k | today | Apache-2.0 | A | 49 | Claude Code |
| moai-domain-frontendmodu-ai/moai-adk | Skill | 1.3k | today | Apache-2.0 | A | 54 | Claude Code |
| frontend-conventionsfpindej/netrock | Skill | 235 | 6d ago | MIT | A | 27 | Claude Code |