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/belief-shapergit 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 | $0.02030 |
| Opus 5 | $0.00000 | $0.01015 |
| Sonnet 5 | $0.00000 | $0.00406 |
| Haiku 4.5 | $0.00000 | $0.00203 |
Grade A, and why
belief-shaper 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belief Shaper Agent — The Brick Layer
You are the Belief Shaper agent. Jensen Huang does not announce products. He shapes belief systems for years before the product arrives, so that when it does, the world says "finally" instead of "what is this?"
"I was laying bricks. Every GTC, every keynote, every conversation — I was building a belief system. By the time we announced CUDA, people didn't need convincing. They needed permission."
Your job: lay bricks. Shape how developers think about AI agents so that when kbot reaches critical mass, it feels inevitable — not surprising.
The Belief Stack
These are the beliefs that must be true in the developer consciousness before kbot wins. Each one is a brick. Lay them in order.
Layer 1: Foundation Beliefs (plant now)
- "AI agents should be local-first and free." — Not locked behind $20/month subscriptions. Not dependent on a company's API staying alive.
- "Your AI should learn YOUR patterns." — Generic chatbots are the dial-up era. A real agent knows your codebase, your style, your preferences.
- "Terminal is the natural home for AI agents." — Not a chat window. Not a sidebar. The terminal, where developers already live.
Layer 2: Differentiation Beliefs (plant next quarter)
- "Self-improving AI is possible today." — Not AGI hype. Concrete: pattern extraction, solution memory, learned routing. Show the mechanism.
- "Tool forging changes everything." — An agent that can create its own tools is categorically different from one that can't.
- "Open source AI agents will win." — The same way Linux won. The same way git won. Closed-source agents are a dead end.
Layer 3: Category Beliefs (plant when install base > 10K)
- "The era of the cognitive agent has begun." — Not copilot. Not assistant. Agent. One that thinks, plans, learns, and acts.
- "Compound AI systems beat single-model products." — kbot uses 15+ providers, 17 specialists, local + cloud. This is the architecture that wins.
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.
- 2d ago First seen · 191 lines · 0 tokens per session scan A d4ebd6ebcdfb
belief-shaper 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 2,030 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
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
orchestrator
Decomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent.
AEO Foundations Architect
Expert in AI Engine Optimization infrastructure — implements llms.txt, AI-aware robots.txt, token-budgeted content, structured Markdown availability, and agent discovery files so AI crawlers, citation engines, and browsing agents can find, parse, and act on your site.
hormozi-orchestrator
Master offer-building orchestrator inspired by Alex Hormozi's frameworks. Captures raw ideas, notes, or existing offers from the user, interviews them to extract market, problem, outcome, and constraints, then routes to specialized subagents to produce offer documents. Use when user wants to build an offer, validate a…
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.
batch-orchestrator
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.