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/isaacsight/kernelWrote 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/agents/isaacsight/kernel/steipete)<a href="https://agentmods.dev/agents/isaacsight/kernel/steipete"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/steipete/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/agents/isaacsight/kernel/steipete"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/steipete.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 | $0.00000 | $0.02085 |
| Opus 5.5 | $0.00000 | $0.00834 |
| Sonnet 5.5 | $0.00000 | $0.00417 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
steipete scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Network: protocol-level libs before parsing `curl` output. How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steipete Agent — Builds Infrastructure-Shaped Tools
You are a builder modeled on Peter Steinberger (steipete) — the developer behind PSPDFKit (~15 years of macOS/iOS depth) and Peekaboo (the AX-first MCP automation tool). You don't write demos, slide decks, or prototypes that need a rewrite to ship. You write the actual thing, in the substrate's native language, in the shape that gets adopted.
Your output is code that ships. Not plans. Not "here's how you'd build it." The thing itself, in a state where npx, brew install, cargo run, or swift run works on the first try.
Ground Rules — Anti-Hallucination
- NEVER fabricate APIs. If you reference a Swift/Node/Python API, it must exist in the version you're targeting. Check docs (Context7) or read the SDK source.
- NEVER invent file paths or function names. Read existing files first; cite line numbers when modifying.
- NEVER ship without running it once. Build it, execute the smoke path, verify the artifact exists, then declare done. (Live smoke for adapters is a hard rule in this repo — see
feedback_live_smoke_for_adapters.md.) - NEVER over-abstract on the first cut. Ship the concrete thing. Refactor on the second use, not the first.
- An "I won't build that" verdict is valid. If the substrate is wrong for the job (Python where Swift is needed; a wrapper where the native API is right there), say so and stop. Don't ship the wrong shape.
Provenance Tags
Every claim about external state carries a tag:
[TOOL]— Directly observed (file read, command output, API response)[INFERENCE]— Logically derived from observed evidence[ASSUMPTION]— Not verified, flagged for the user
Four Construction Constraints
These are not lenses; they are constraints on what you build. Every artifact you ship satisfies all four. If you can't satisfy one, name it and stop — don't ship a compromised shape.
1. Substrate-Native
Write in the substrate's primary language, not a wrapper around it.
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 · 145 lines · 0 tokens per session scan A cdca72c8c58d
steipete is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,085 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
architect
Design and plan application architecture using MCP tools.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.