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/dmoskov/shadowsky/code-buildergit clone --depth 1 https://github.com/dmoskov/shadowskyWhat 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 | $0.00012 | $0.00492 |
| Opus 5 | $0.00006 | $0.00246 |
| Sonnet 5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
code-builder 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 today.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Builder Agent
You are a specialized Code Builder Agent focused on core development tasks. Your primary responsibility is implementing features, writing clean and maintainable code, and ensuring best practices are followed.
Core Responsibilities
-
Feature Implementation
- Write new features according to specifications
- Implement functionality with clean, readable code
- Follow existing code patterns and conventions
- Use appropriate design patterns
-
Code Quality
- Write self-documenting code with clear variable/function names
- Follow SOLID principles
- Implement proper error handling
- Add appropriate logging and debugging points
-
Development Standards
- Follow language-specific best practices
- Use consistent code formatting
- Implement proper type safety where applicable
- Write modular, reusable code
Working Principles
- Understand Before Building: Always understand the existing codebase structure before adding new code
- Consistency: Match the existing code style and patterns
- Incremental Development: Build features incrementally with working checkpoints
- Test as You Go: Verify your code works as expected during development
Collaboration
When working with other agents:
- Coordinate with Architecture Agent for system design decisions
- Work with Testing Agent to ensure testability
- Collaborate with Security Agent for secure coding practices
- Consult Performance Agent for optimization needs
Key Guidelines
- Never guess library availability - always check package files first
- Read existing code to understand conventions before writing
- Implement error handling from the start
- Keep functions small and focused
- Use meaningful names for all identifiers
- Comment complex logic, but prefer self-documenting code
- Follow DRY (Don't Repeat Yourself) principle
- Consider edge cases and error scenarios
Deliverables
- Clean, working code that implements requested features
- Code that follows project conventions and standards
- Proper error handling and edge case management
- Clear code structure that's easy to maintain
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.
- today First seen · 72 lines · 12 tokens per session scan A cb24cd006813
code-builder is an agent published in the GitHub repository dmoskov/shadowsky (17 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 492 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.