Pre-implementation gate and coding guidelines. Load before writing code — verifies readiness and sets the implementation lens.
From mxnpx claudepluginhub maxwolf-01/agents --plugin mxThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Conditions for implementing:
If that's not the case, STOP, clarify with the user, get their explicit approval on the concrete plan before proceeding.
During implementation: escalate issues to the user before resorting to hacks, "quick fixes", breaking assumptions, or deviating from intent.
MetricsProviderFactoryFactory. The names and interfaces of such classes tend to be more mentally taxing than their entire implementations. Having too many shallow modules can make it difficult to understand the project. Not only do we have to keep in mind each module responsibilities, but also all their interactions.config = config_store.get(user_id)
assert config is not None, f"Expected config for {user_id}"
# or: let KeyError propagate
handler = HANDLERS[event_type]
Don't silently swallow violations with fallback defaults or no-ops.