Nm Leyline Progressive Loading

Context-aware progressive module loading with hub-and-spoke pattern for token optimization. progressive loading, lazy loading, hub-spoke, module selection.

This skill is primarily documentation for building progressive-loading behaviors and is internally coherent with that purpose, but review carefully before giving an agent permission to run it: - The SKILL.md encourages detecting files (.git, .py), scanning directory structure, and running local python scripts — these actions access your workspace and can expose code or metadata. Be explicit about whether you want an agent to scan your files. - The performance doc refers to an env var (SLASH_COMMAND_TOOL_CHAR_BUDGET) that is not declared as required; confirm whether the agent will read or rely on that env var. - The skill requires a config path (night-market.leyline:mecw-patterns); inspect that config to ensure it doesn't contain secrets or sensitive pointers. - Because this is instruction-only, no new binaries or network installs are introduced by the package itself, but the agent following these instructions could execute local scripts or load other skills. If you plan to enable autonomous invocation, restrict file and env access or run in a sandbox until you verify behavior. What would reduce my concern: explicit, narrow statements in the SKILL.md that specify what files/configs are read, a declaration of any env vars used, and an explicit note that no network exfiltration or broad filesystem scans will be performed. If the skill is only used as offline documentation (no agent execution), the practical risk is much lower.

Type: OpenClaw Skill Name: nm-leyline-progressive-loading Version: 1.0.0 The skill bundle provides architectural patterns and documentation for optimizing AI agent context windows through progressive module loading and token budgeting. The included files (SKILL.md and various modules) contain illustrative Python snippets and Markdown instructions for managing dynamic module selection based on user intent and environment signals. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the content is entirely aligned with its stated purpose of performance optimization within the Claude Night Market ecosystem.