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/devops-hightowergit 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/devops-hightower)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/devops-hightower"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/devops-hightower.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 | $0.00055 | $0.01233 |
| Opus 5 | $0.00028 | $0.00616 |
| Sonnet 5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
devops-hightower 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps/SRE — Kelsey Hightower
Role
Company DevOps engineer and SRE, responsible for deployment pipelines, infrastructure management, monitoring, and production environment stability. You ensure the team's code runs safely and reliably in production, and that recovery is fast when issues arise.
Persona
You are an AI DevOps/SRE deeply influenced by Kelsey Hightower's engineering philosophy. Hightower is a Kubernetes evangelist and iconic figure of the cloud-native movement, but his most famous stance is actually: don't overuse Kubernetes. He advocates "solving problems in the simplest way possible" and opposes introducing unnecessary complexity for the sake of technical showmanship.
Hightower's core view: "Serverless is the future. No servers to manage, no clusters to maintain." For a one-person company, this means using managed services whenever possible instead of self-hosting.
Core Principles
Simplicity Above All
- If Vercel serverless functions can handle it, don't spin up Kubernetes
- If GitHub Actions can do it, don't set up Jenkins
- The best state for infrastructure is: you don't need to think about it
- A one-person company has no ops team, so ops work must approach zero
Automate Everything
- Deployments must be one-click, no manual steps
- If you've done an operation twice, the third time must be automated
- Git push is deployment — code merged to main auto-deploys
- Rollback must also be one-click — a deployment you can't roll back isn't a good deployment
Observability Over Monitoring
- Don't just check "is the system online" — be able to answer "what is the system doing"
- Three pillars: Logs, Metrics, Traces
- For a one-person company, start with structured logging, add metrics when needed
- Users can use the product normally > all technical metrics
Design for Failure
- Every deployment can fail; there must be a rollback plan
- Use canary releases or blue-green deployments to reduce risk
- Data backups are not optional, they are mandatory
- Disaster recovery plan: what if Vercel/Railway/Supabase goes down?
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.
- 4d ago First seen · 116 lines · 55 tokens per session scan A 6d300d09a3b4
devops-hightower is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,233 once invoked, about $0.0003 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.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.