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.
git clone --depth 1 https://github.com/erichare/skillrouteWrote 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/plugins/erichare/skillroute/claude-plugin)<a href="https://agentmods.dev/plugins/erichare/skillroute/claude-plugin"><img src="https://agentmods.dev/badge/plugins/erichare/skillroute/claude-plugin/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/plugins/erichare/skillroute/claude-plugin"><img src="https://agentmods.dev/badge/plugins/erichare/skillroute/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
skillroute 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 18d 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "skillroute",
"displayName": "SkillRoute",
"version": "0.5.0",
"description": "Local-first skill routing for Claude Code: index your SKILL.md bundles once, then ask SkillRoute which skills fit a request. It ranks candidates with reasons, confidence, and evidence, and asks clarifying questions when a request is ambiguous.",
"author": {
"name": "Eric Hare",
"email": "[email protected]",
"url": "https://github.com/erichare"
},
"homepage": "https://github.com/erichare/skillroute",
"repository": "https://github.com/erichare/skillroute",
"documentationUrl": "https://github.com/erichare/skillroute/tree/main/claude-plugin#readme",
"supportUrl": "https://github.com/erichare/skillroute/issues",
"privacyPolicyUrl": "https://github.com/erichare/skillroute/tree/main/claude-plugin#privacy",
"license": "MIT",
"keywords": [
"skills",
"agent-skills",
"skill-routing",
"skill-catalog",
"mcp",
"retrieval"
],
"mcpServers": {
"skillroute": {
"command": "npx",
"args": [
"-y",
"@skillroute/[email protected]"
]
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 67 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
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.
- 18d ago First seen · 36 lines scan A be7b8da45756
skillroute is a plugin published in the GitHub repository erichare/skillroute (41 stars, last pushed 19d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-29.
Other plugins, from other repositories
blz
Fast local documentation search with llms.txt indexing. Search 12K+ line docs in 6ms with line-accurate citations. One command (/blz) and one agent (@blz:blazer) for all documentation operations.
smriti
Local-first persistent memory for AI agents. One brain, every agent, zero cloud. Capture, search, and recall across all your Claude sessions using semantic vector search.
harness-platform
8 skills: Operate delegates, IaCM workspaces, cloud development environments, artifact registries, SBOMs, supply chain and pull requests.
tree-ring-memory
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
claude-superskills marketplace
Plugin marketplace listing 1 plugin: claude-superskills.
collate
A plugin that provides an end-to-end workflow for OCR and proofreading historical Chinese documents. OCR turns scanned page images into editable text.