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/shinpr/sub-agents-skillsWrote 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/shinpr/sub-agents-skills/sub-agents-skills)<a href="https://agentmods.dev/plugins/shinpr/sub-agents-skills/sub-agents-skills"><img src="https://agentmods.dev/badge/plugins/shinpr/sub-agents-skills/sub-agents-skills.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
runner 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.
What it actually says
{
"name": "runner",
"description": "Run agent definitions as sub-agents across multiple AI coding CLIs.",
"version": "0.13.2",
"author": {
"name": "Shinsuke Kagawa",
"url": "https://github.com/shinpr"
},
"homepage": "https://github.com/shinpr/sub-agents-skills",
"repository": "https://github.com/shinpr/sub-agents-skills.git",
"license": "MIT",
"keywords": [
"sub-agents",
"agent-skills",
"orchestration",
"codex",
"claude-code",
"cursor",
"glm",
"kimi",
"z.ai",
"grok",
"antigravity",
"gemini",
"opencode",
"command-code"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 38 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.
- 2d ago Changed fc690679ff4c
- 7d ago First seen · 29 lines scan A 6aa6e80d3b2c
runner is a plugin published in the GitHub repository shinpr/sub-agents-skills (83 stars, last pushed 5d 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 2026-08-30.
Other plugins, from other repositories
rosetta-light
Rosetta for Claude - Software Engineering Accelerator instruction set, workflows, and guardrails. (lightweight: simpler workflows, smaller models).
toolport
Every tool. One port. Connects this agent to your local Toolport gateway: every MCP server you set up in Toolport, exposed through a handful of compact meta-tools instead of hundreds of tool definitions (90% fewer tokens, measured).
forensic-deepdive
Persistent code knowledge graph + 9 composite MCP tools (impact, context, archaeology, flow, query, recordinsight, recallinsights, visualize, trace) for AI coding agents.
spar
Keep learning while AI writes the code. Predict before you are told, then turn every gap between your model and reality into a curriculum.
seqwalk
Walk through AI-written code with interactive HTML sequence diagrams.
codetape
The flight recorder for AI coding — keeps your docs in sync with your code.