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/plato-corp/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/plato-corp/skills/tiro)<a href="https://agentmods.dev/plugins/plato-corp/skills/tiro"><img src="https://agentmods.dev/badge/plugins/plato-corp/skills/tiro/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/plato-corp/skills/tiro"><img src="https://agentmods.dev/badge/plugins/plato-corp/skills/tiro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tiro 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 1mo 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": "tiro",
"version": "0.1.0",
"description": "LLM Wiki suite from the Tiro team — bootstrap, ingest, query, lint, socratic, sync. A persistent, agent-maintained personal knowledge base.",
"author": {
"name": "ThePlato",
"email": "[email protected]"
},
"homepage": "https://github.com/plato-corp/skills",
"repository": "https://github.com/plato-corp/skills",
"keywords": [
"llm-wiki",
"knowledge-base",
"second-brain",
"socratic",
"tiro",
"karpathy"
]
}
What it installs
The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 368 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 20 lines scan A dd23f51c28ed
tiro is a plugin published in the GitHub repository plato-corp/skills (10 stars, last pushed 2d 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 2026-08-31.
Other plugins, from other repositories
basemind
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB.
basemind
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB.
agent-memory
Agent Memory & Knowledge: filesystem memory, RLM summary ledgers, vector retrieval, and Obsidian vault and wiki workflows.
ultron-memory
Expone la memoria personal de ULTRON (brain.db + Qdrant, recall hibrido BM25+E5) y el buscador de papers academicos (OpenAlex + Semantic Scholar) como servidores MCP locales de solo lectura, con los 3 hooks minimos de memoria (resume al abrir, gate socratico por prompt, captura al cerrar), para chat, Claude Desktop y…
agent-kb
Project knowledge base for coding agents: Qdrant-backed semantic search over your docs, ontology bindings, and make targets, exposed over MCP, with an operating skill that teaches the agent when to search.
claude-token-reducer
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.