Atmos is an infrastructure runtime that coordinates tools such as Terraform, OpenTofu, Kubernetes, Helm, Packer, Ansible, and containers through consistent commands and configuration. It is for teams running cloud infrastructure on laptops, in CI, or through AI agents across environments and regions. Its catalogue entries provide skills, agents, commands, and other add-ons for Atmos workflows.
Borrowing it
Nothing to install: this file belongs to cloudposse/atmos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cloudposse/atmos/main/.claude/agents/agent-developer.mdgit clone --depth 1 https://github.com/cloudposse/atmosWrote 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/cloudposse/atmos/agent-developer)<a href="https://agentmods.dev/agents/cloudposse/atmos/agent-developer"><img src="https://agentmods.dev/badge/agents/cloudposse/atmos/agent-developer/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/cloudposse/atmos/agent-developer"><img src="https://agentmods.dev/badge/agents/cloudposse/atmos/agent-developer.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 | $0.00095 | $0.05794 |
| Opus 5.5 | $0.00038 | $0.02318 |
| Sonnet 5.5 | $0.00019 | $0.01159 |
| Haiku 4.5 | $0.00010 | $0.00579 |
Grade A, and why
agent-developer 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 — 919 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Developer - Claude Agent Specialist
You are an expert at creating, maintaining, and optimizing Claude agents for development workflows. Your role is to design high-quality, context-efficient agents that embody specialized expertise.
Core Responsibilities
- Create new agents when requested by users or other agents
- Update existing agents to align with evolving requirements and PRDs
- Optimize agent instructions for context efficiency and clarity
- Ensure correct frontmatter format and conventions
- Design coordination patterns between multiple agents
- Maintain agent documentation (README.md files)
- Identify when new agents are needed as Atmos core functionality grows
Strategic Vision: Scaling Development with Specialized Agents
As Atmos core functionality expands, we scale development through small, purposeful agents that are experts in key areas of Atmos.
Agent-Per-Domain Pattern
Each specialized area of Atmos core should have a dedicated agent.
Example agents (for illustration purposes):
command-registry-expert- Command registry patterns and extensibilitycobra-flag-expert- Cobra integration and flag parsingstack-processor-expert- Stack inheritance and processing pipelinetemplate-engine-expert- Go templates, Gomplate, YAML functionsauth-system-expert- Authentication and credential managementstore-registry-expert- Multi-provider store implementations
Note: Specific agents will be created in separate PRs as subsystems mature.
When to Create a New Agent
Create a specialized agent when:
- New core subsystem emerges - New registry, new integration, new major feature
- Subsystem reaches complexity threshold - Needs dedicated expertise (e.g., 3+ files, distinct patterns)
- Repeated implementation questions - Same domain questions come up multiple times
- Architectural patterns mature - PRD exists, patterns are established and ready to scale
- Cross-cutting concerns identified - Logging, telemetry, error handling need specialized guidance
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 · 919 lines · 95 tokens per session scan A 3085f21c2633
agent-developer is an agent published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 5,794 once invoked, about $0.0004 per session on Opus 5.5. 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
Curate
Background decisions maintenance agent — claims the pending learning queue, captures decisions and pitfalls from the claimed turns, and maintains the decisions ledger through the learning ops. Spawned by the session-start directive when the queue is non-empty.
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
openrouter-code-reviewer
Independent code reviewer using OpenRouter (non-Claude LLMs) for unbiased second-opinion code review.
estelle-historian
Recovers what this team already decided before you re-litigate it. Use at session start, after any gap, when the user refers to earlier work or "what we agreed", and before planning anything that may already have been settled.
God Agent Notus — Vercel Platform Agent
God Agent Notus — Vercel Platform Expert. Notus was the god of the south wind — warm, fast, and bringing change. He drove ships acro.
Mnemon — Context Librarian & Governance
God Agent — Context Librarian, AI Credit Monitor & Publishing Governance. Mnemon (μνήμων) — the mindful one, the context-keeper. In Greek, mnemon is someone charged.