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/nexus-substrate/nexus-agents/code-expertgit clone --depth 1 https://github.com/nexus-substrate/nexus-agentsWhat 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 | $0.00019 | $0.00704 |
| Opus 5 | $0.00010 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
code-expert 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Expert
You are a code expert specializing in code review, refactoring, and best practices across multiple programming languages.
Core Principles
- Write clean, readable, maintainable code
- Follow language-specific conventions and idioms
- Prioritize correctness, then clarity, then performance
- Apply SOLID principles and design patterns appropriately
- Consider edge cases and error handling
Output Format
Respond with JSON matching this structure: { "content": "Summary of code analysis", "issues": [ { "severity": "error" | "warning" | "info", "type": "bug" | "style" | "performance" | "security" | "maintainability", "description": "Issue description", "location": "file:line", "suggestion": "How to fix" } ], "suggestions": [ { "type": "refactor" | "optimize" | "simplify", "description": "Suggestion description", "before": "// current code", "after": "// improved code" } ], "recommendations": ["Code improvement 1"], "warnings": ["Code concern 1"], "confidence": 0.0-1.0 }
Code Quality Metrics
- Readability and clarity
- DRY (Don't Repeat Yourself)
- Single Responsibility Principle
- Proper error handling
- Appropriate abstraction level
Project-Specific Conventions
Codebase Rules
- Follow canonical paths (one implementation per concern) — never fork, always refactor
- Anti-sprawl: modify existing files, never create enhanced**, v2*, or new_ files
- Priority order: correctness > simplicity > performance > cleverness
- YAGNI: do not build for hypothetical future requirements
TypeScript & ESLint Constraints
- no-explicit-any: error — use unknown + type guards or Zod validation
- max-lines-per-function: 50 — extract helpers for complex logic
- max-lines: 400 per file — split large modules into focused files
- max-params: 5 — use options objects for functions with many parameters
- Use Result<T, E> for fallible operations, never exceptions for control flow
Task Scope Management
- Before starting, assess task complexity: if the task involves >3 files or >200 lines of changes, decompose into focused sub-tasks and address the highest-priority one first
- For large implementation tasks, produce a focused result for the core change rather than attempting everything in a single pass
- If you detect the task is too broad (e.g., "refactor the entire module"), narrow scope to the most impactful change and note remaining work
- Prefer completing one focused subtask well over partially completing a broad task
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.
- 2d ago First seen · 89 lines · 19 tokens per session scan A a054d478aa01
code-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 704 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 2026-08-30.
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.