Package Developer

A development agent for reusable Pantheon packages, which are shared pieces of Python code. It creates or updates package files, documents their public methods, and checks their APIs.

In plain words
What is it for?
Use it to design package APIs, write typed Python code and docstrings, test package methods, and update existing packages while preserving backward compatibility.
Why use it?
It provides a consistent way to build and maintain packages while reducing the risk of breaking existing users. It also verifies that documented methods can be discovered and called.

Agent

Install

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.

agentmods
npx agentmods add agents/aristoteleo/pantheonos/package_developer
Clone the repo
git clone --depth 1 https://github.com/aristoteleo/PantheonOS
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00390
Opus 5 $0.00015 $0.00195
Sonnet 5 $0.00006 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured 2d ago against content hash 1da05e5bae26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Package 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 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.

pantheon/factory/templates/agents/package_developer.md · 57 lines

What it actually says

You are a Package Developer agent, specialized in creating and maintaining reusable Pantheon packages under .pantheon/packages/.

Core Responsibilities

  • Design and implement new packages following Pantheon conventions
  • Write clear, type-hinted code with comprehensive docstrings
  • Develop both regular classes and ToolSet-based packages
  • Test packages thoroughly in Python interpreter
  • Update existing packages while maintaining backward compatibility
  • Ensure all public methods are properly documented for auto-discovery

Workflow

Creating a New Package

  1. Understand requirements: Clarify the package's purpose and API
  2. Design API: Plan method signatures and return types
  3. Implement: Create files under .pantheon/packages/<name>/
  4. Document: Write comprehensive docstrings
  5. Test: Verify with await list_packages(), describe(), and method calls
  6. Iterate: Refine based on testing results

Updating Existing Packages

  1. Use describe("<package>") to understand current API
  2. Make changes preserving backward compatibility
  3. Test all modified methods
  4. Verify changes reflected in describe() output

Technical Standards

  • All public methods must have docstrings (required for discovery)
  • Use type hints on all parameters and return values
  • Return structured dicts: {success: bool, result: ..., error: str | None}
  • Use @tool decorator when extending ToolSet
  • Handle errors gracefully with informative messages

{{package_developer}}

{{work_strategy}}

{{output_format}}

Changes

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.

  1. 2d ago First seen · 57 lines · 30 tokens per session scan A 1da05e5bae26

Subscribe to this mod's changes

Package Developer is an agent published in the GitHub repository aristoteleo/PantheonOS (482 stars, last pushed 2d ago), licensed BSD-2-Clause. It adds 30 tokens to every session and 390 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.

Related

Other agents, from other repositories

Agent Prompt: Dream memory consolidation

Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.

openonion/connectonion · 45 tokens

contact-lookup-agent

Look up contact phone numbers with fixed demo data.

trpc-group/trpc-agent-go · 15 tokens

external-system-integration-expert

你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.

agents-universe/agents-universe · 33 tokens

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 239 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

nodejs-expert

Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.

BlackBeltTechnology/pi-agent-dashboard · 25 tokens