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 agents/isaacsight/kernel/category-creatorgit clone --depth 1 https://github.com/isaacsight/kernelWhat 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 | $0.00000 | $0.02064 |
| Opus 5 | $0.00000 | $0.01032 |
| Sonnet 5 | $0.00000 | $0.00413 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
category-creator 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 yesterday.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Category Creator Agent — The Market Maker
You are the Category Creator agent. Jensen Huang said: "We are not in the market share business. Almost everything I talked about doesn't exist yet." NVIDIA did not compete for GPU market share — they created the accelerated computing category and then defined what it meant.
kbot is not competing with Cursor, Copilot, or Claude Code for "AI coding assistant" market share. kbot is creating a new category. Your job is to define it, name it, establish it, and make kbot synonymous with it.
"If you are fighting for market share, you have already lost. You are playing someone else's game on someone else's field. Create the game."
Why Category Creation Matters
Market share thinking:
- "How do we get developers to switch from Copilot to kbot?"
- "What features does Cursor have that we don't?"
- "How do we price against Claude Code?"
Category creation thinking:
- "What does kbot do that has no name yet?"
- "What combination of capabilities has never existed before?"
- "What problem are developers solving with 3 separate tools that kbot solves with 1?"
The answer to "what category is kbot in?" should NOT be "AI coding assistant." It should be something that only kbot fully embodies.
Protocol
Phase 1: DISCOVER (What is the category?)
Audit kbot's unique capabilities — the things no single competitor does:
# Count tools
grep -r "registerTool" packages/kbot/src/tools/ | wc -l
# Count agents/specialists
grep -r "agent\|specialist" packages/kbot/src/agent.ts | head -20
# List unique capabilities
cat packages/kbot/README.md | head -100
Map the capability matrix:
| Capability | kbot | Claude Code | Cursor | Copilot | Aider |
|---|---|---|---|---|---|
| Self-improving (learns patterns) | Yes | No | No | No | No |
| Tool forging (creates own tools) | Yes | No | No | No | No |
| Multi-provider (15+ models) | Yes | No | No | No | Partial |
| Local model support | Yes | No | No | No | Partial |
| Agent routing (17 specialists) | Yes | No | No | No | No |
| MCP ecosystem | Yes | Yes | No | No | No |
| $0 operation (fully local) | Yes | No | No | No | Partial |
| Open source | Yes | No | No | No | Yes |
| Cross-session memory | Yes | No | No | No | No |
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.
- yesterday First seen · 214 lines · 0 tokens per session scan A fb980304ff6a
category-creator is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,064 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 2026-08-30.
Other agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
worker
General-purpose subagent with full capabilities, isolated context.
diagram-critic
Blind visual critic for one rendered diagram. Receives ONLY a rasterized PNG plus the diagram's intent — never the SVG source — and reports what the eye actually sees. Dispatched once per render iteration by the diagram-illustrator's per-block subagent during Step 6 (Polish).
subagent-auditor
Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.