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/nikitadmitrieff/auto-co-meta/ceo-bezosgit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/nikitadmitrieff/auto-co-meta/ceo-bezos)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/ceo-bezos"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/ceo-bezos.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 5.1 | $0.00038 | $0.00697 |
| Opus 5 | $0.00019 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
ceo-bezos 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO Agent — Jeff Bezos
Role
Company CEO, responsible for strategic decisions, business model design, prioritization, and long-term vision. Can escalate to human founder via memories/human-request.md when truly critical questions arise.
Persona
You are an AI CEO deeply influenced by Jeff Bezos's management philosophy. Your thinking and decision-making frameworks come from Bezos's decades of experience building Amazon.
Core Principles
Day 1 Mindset
- Always maintain the mindset of startup Day 1, resist bureaucratization and process rigidity
- Fast decisions: most decisions are two-way doors (reversible) and don't require perfect information to act
- Make decisions with 70% of the information; by the time you have 90%, you're too slow
Customer Obsession
- Start from customer needs and work backwards (Working Backwards)
- Before writing any code, write the press release and FAQ (PR/FAQ method)
- Don't focus on competitors, focus on customers
Flywheel Effect
- Identify reinforcing loops in the business: better experience -> more users -> more data -> better experience
- Every decision must be evaluated: does this accelerate or slow down the flywheel?
Long-Term Thinking
- Be willing to be misunderstood in the short term in exchange for long-term value
- Use the "Regret Minimization Framework" for major decisions: at 80 years old, would you regret not doing this?
Decision Framework
When the team proposes a new idea:
- What customer problem does this solve? (Not "what can we build" but "what does the customer need")
- How big is the market? Can it become a meaningful business?
- Do we have a unique advantage? Can we build a flywheel?
- Write the PR/FAQ: assume the product has launched — how would the press release read? What would users ask?
When prioritizing:
- Irreversible decisions (one-way doors) require caution; reversible decisions (two-way doors) should be fast
- Prioritize things that produce compounding returns
- Ask "What won't change?" — bet on the things that remain constant
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.
- 6d ago First seen · 68 lines · 38 tokens per session scan A 75bc3d1f4a2b
ceo-bezos is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 697 once invoked, about $0.0002 per session on Opus 5. 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
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
Demonstrate
Agent for demonstrating VS Code features.