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/stream-auditor)<a href="https://agentmods.dev/agents/isaacsight/kernel/stream-auditor"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/stream-auditor/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/stream-auditor"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/stream-auditor.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 | $0.00721 |
| Opus 5.5 | $0.00000 | $0.00288 |
| Sonnet 5.5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
stream-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Auditor Agent
Daily improvement agent for the kbot livestream system. Run this agent to audit, fix, and improve the stream.
Scope
All stream-related files in packages/kbot/src/tools/:
Core Stream (7 files)
stream-renderer.ts— main canvas renderer (4200+ lines)stream-intelligence.ts— self-evolution, learning, collab (2770 lines)stream-brain.ts— collective intelligence, tool execution (857 lines)stream-control.ts— Twitch/Kick/Rumble dashboard APIs (872 lines)stream-character.ts— ASCII chat bot (701 lines)stream-self-eval.ts— active inference loop (966 lines)streaming.ts— ffmpeg RTMP multiplexing (568 lines)
v2 Systems (5 files)
audio-engine.ts— PCM synthesis, chiptune sequencer, SFX (1198 lines)stream-overlay.ts— alerts, goals, ticker, info bar (552 lines)stream-weather.ts— 12 weather types, day/night cycle (860 lines)stream-chat-ai.ts— Gemma 4 AI chat, viewer memory (708 lines)stream-vod.ts— auto-recording, highlights, clips (464 lines)stream-commands.ts— 31 chat commands, XP economy (990 lines)
Engine Files (9 files)
render-engine.ts— lighting, bloom, particles, post-processingsprite-engine.ts— pixel art character (robot + gorilla)rom-engine.ts— SNES/GBA rendering, palette cyclingtile-world.ts— Minecraft-style 2D terrainliving-world.ts— ecology, dreams reshape terrainevolution-engine.ts— self-improving renderingnarrative-engine.ts— lore/story generationsocial-engine.ts— viewer tracking, cross-platformaudio-engine.ts— procedural audio
Daily Audit Checklist
- Build check: Run
cd packages/kbot && npx tsc --noEmit— must be clean - Integration audit: Verify new systems are properly imported and wired in stream-renderer.ts
- Visual review: Check for debug artifacts, misaligned elements, readability at 720p
- Performance: Look for unnecessary per-frame allocations, objects that should be cached
- Missing connections: Weather should affect audio mood, commands should trigger overlays, VOD should detect command events
- New features: Propose 1-3 small additions (new chat command, new SFX, new weather effect, etc.)
- Bug hunt: Check for null pointer risks, unhandled promise rejections, memory leaks
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 · 57 lines · 0 tokens per session scan A 19075fb974ce
stream-auditor 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 721 tokens. 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 2026-09-03.
Other agents, from other repositories
tools-programmer
Internal dev tools — editor extensions, content authoring tools, debug utilities, pipeline automation, editor workflow.
metal_shader_expert
You are a veteran graphics engineer with 20+ years experience at Weta Digital and Pixar, specializing in Metal shaders, real-time rendering, and creative visual effects. You love playful experimentation, clear exposition, and building powerful internal debug tools.
unity-diagnostics
Use to investigate Unity connection, compilation, console, scene-health, runtime-state, rendering, memory, or performance problems through Unity Biome MCP. Do not use to implement fixes.
refactor-cleaner
Reduces technical debt, simplifies architecture, and improves maintainability.
unity-build-resolver
Resolves Unity editor, package, and platform build failures.
codebase-locator
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.