By c-hoeller
Senior coding standards as Engineering Tenets, auto-loaded into every Claude Code session.
Use when keeping a member private when a test wants to call it directly; testing a class whose helper is private/protected/internal and the test cannot reach it; deciding how to test logic that currently lives behind a `private`/`protected` modifier; reviewing a diff that widens an access modifier with a justification referencing tests.
Use when handling an error you do not know how to recover from in the current scope; writing a `catch` / `except` / `.catch()` block that does nothing or only logs; reviewing a diff that adds a try/catch around new code without rethrow or remediation; deciding what to do with a Promise/Task whose failure path has no obvious owner.
Use when adding a null/range/format check inside an internal helper that already receives a typed argument; deciding where to validate input that crosses a trust boundary (HTTP handler, CLI args, queue message, deserializer); reviewing a diff that scatters defensive guards through the call graph below the entry point; writing parsing/coercion logic that turns external data into a domain type.
Use when writing a test that verifies a mock was called instead of the effect the call produced; reaching for a spy/stub/inspector to peek at internal state from a test; reviewing a test that breaks every time the production code is refactored; deciding what to assert about a function whose contract is "given X, the world looks like Y".
Use when writing a comment that paraphrases the line of code immediately below it; adding a docstring to a function whose name and signature already say everything; reviewing a diff that adds explanatory comments to make obvious code "easier to read"; deciding whether a non-obvious decision (workaround, constraint, invariant) needs a comment.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace by omnivex labs.
| Name | What it does |
|---|---|
| warden | Senior coding standards as Engineering Tenets, auto-loaded into every Claude Code session. |
In a Claude Code session:
/plugin marketplace add <git-url-of-this-repo>
/plugin install warden@claude-plugins
The marketplace exposes each plugin as a separate installable. Install only what you want; plugins are independent.
.
├── .claude-plugin/
│ └── marketplace.json # marketplace manifest, lists all plugins
├── plugins/
│ └── warden/ # one plugin per subdirectory
└── README.md
Each plugins/<name>/ directory is a self-contained Claude Code
plugin with its own .claude-plugin/plugin.json, hooks/, skills/,
and content.
MIT
npx claudepluginhub c-hoeller/agent-plugins --plugin wardenFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses