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 commands/jezweb/claude-skills/tanstack-startgit clone --depth 1 https://github.com/jezweb/claude-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/commands/jezweb/claude-skills/tanstack-start)<a href="https://agentmods.dev/commands/jezweb/claude-skills/tanstack-start"><img src="https://agentmods.dev/badge/commands/jezweb/claude-skills/tanstack-start.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00101 |
| Opus 5 | $0.00007 | $0.00051 |
| Sonnet 5 | $0.00003 | $0.00020 |
| Haiku 4.5 | $0.00001 | $0.00010 |
Grade B, and why
tanstack-start scanned grade B with 1 finding 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 4d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
allowed-tools: "*" What it actually says
Load the tanstack-start skill and build a complete app.
If $ARGUMENTS contains a project name, use it. Otherwise, ask for project details.
The skill generates every file from scratch — no template clone. Workflow: gather info → initialise project → database + auth → app shell → routes + dashboard → verify → deploy.
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.
- 4d ago First seen · 12 lines · 14 tokens per session scan B 6fca1b22bd6c
tanstack-start is a command published in the GitHub repository jezweb/claude-skills (993 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 101 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
build-agent
Build an AI agent on Cloudflare using the Agents SDK.
build-mcp
Build a remote MCP server on Cloudflare using McpAgent.
setup-line-harness.en
Lesson command — deploy line-harness-oss to Cloudflare's free tier.
setup
Initialize claude-crawl for this project. Validates API keys and creates output directory.
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.