General Principles
General code quality critique principles
- Type
- Subagent
- Repository
- nyldn/claude-octopus
- GitHub stars
- 4.1k
- License
- MIT
- Repo last updated
- Sep 26, 2026
- Source file
- agents/principles/general.md
What General Principles is
General Principles is a subagent published in the nyldn/claude-octopus repository on GitHub, which has about 4.1k stars. The repository describes itself as: “Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to General Principles and get back a compact result.
How to install General Principles
Claude Code
- Download general.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/principles/general.md, shared under the repository's MIT license. Read the full file on GitHub.
Code MUST adhere to these quality requirements:
Correctness
- Functional Correctness - Code does what it's supposed to do. All requirements are met.
- Edge Case Handling - Boundary conditions are handled. Empty inputs, nulls, and limits work.
- Error Handling - Errors are caught and handled gracefully. No unhandled exceptions.
Reliability
- No Race Conditions - Concurrent access is properly synchronized.
- Resource Management - Resources are acquired late, released early. No leaks.
- Idempotency - Operations that should be idempotent are implemented correctly.
Code Quality
- Readability - Code is clear and understandable. Intent is obvious.
- Simplicity - Solutions are as simple as possible, but no simpler.
- Consistency - Code follows established patterns and conventions.
Best Practices
- Type Safety - Use types effectively. Avoid any/unknown where possible.
- Validation - Input is validated at boundaries. Output is sanitized.
- Logging - Important events are logged. Errors include context.
Architecture
- Modularity - Code is organized into logical modules. Clear boundaries.
- Dependencies - External dependencies are justified and minimal.
- Configuration - Environment-specific values are configurable.
Checklist
When reviewing code, verify:
- Code is functionally correct
- Edge cases are handled
- Errors are handled appropriately
- No obvious bugs or issues
- Code is readable and maintainable
- Follows project conventions
- No unnecessary complexity
- Proper use of types
- Input validation in place
- Appropriate logging
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is General Principles?
General Principles is a subagent for Claude Code and Claude Cowork from the nyldn/claude-octopus repository on GitHub. General code quality critique principles
How do I install General Principles in Claude Code?
Download general.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use General Principles in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is General Principles safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Ui Ux Designer Design UI/UX systems with style guides, color palettes, typography, and component specs. Bridges user research and frontend implementation using BM25 design intelligence. Use PROACTIVELY when designing interfaces or creating design systems. Subagent · nyldn/claude-octopus
- Typescript Pro Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. Use PROACTIVELY for TypeScript architecture, type inference optimization, or advanced typing patterns. Subagent · nyldn/claude-octopus
- Write Intent Principle Announce intent before writing files — one sentence stating what, where, and why, with an idempotence check that skips the Write entirely when state is already correct. Subagent · nyldn/claude-octopus
- Ux Researcher Expert UX researcher specializing in user research synthesis, journey mapping, persona creation, and usability evaluation. Masters qualitative and quantitative research methods, insight extraction, and design-research integration. Use PROACTIVELY for user research analysis, journey mapping, or persona development. Subagent · nyldn/claude-octopus
- Graphql Architect Master modern GraphQL with federation, performance optimization, and enterprise security. Build scalable schemas, implement advanced caching, and design real-time systems. Use PROACTIVELY for GraphQL architecture or performance optimization. Subagent · nyldn/claude-octopus
- Frontend Developer Frontend developer. Delegate only when the user explicitly starts an Octopus workflow. Subagent · nyldn/claude-octopus
- Incident Responder Expert SRE incident responder for rapid resolution, observability, and incident management. Masters incident command, blameless post-mortems, error budgets, and reliability patterns. Use IMMEDIATELY for production incidents or SRE practices. Subagent · nyldn/claude-octopus
- Finance Analyst Expert finance analyst specializing in financial modeling, budgeting, forecasting, ROI/NPV analysis, cash flow management, unit economics, and pricing strategy. Masters spreadsheet-driven analysis and strategic finance. Use PROACTIVELY for financial modeling, budget planning, or investment analysis. Subagent · nyldn/claude-octopus