From necturalabs
Use at the start of every conversation and after every agent handoff or context switch. Ensures global CLAUDE.md and project AGENTS.md are fully loaded and retained in context at all times.
How this skill is triggered — by the user, by Claude, or both
Slash command
/necturalabs:agent-context-loaderThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ensures the agent always operates with full awareness of user-level and project-level instructions. Global `CLAUDE.md` and project `AGENTS.md` must be loaded into context in full — never summarized, truncated, or skipped.
Ensures the agent always operates with full awareness of user-level and project-level instructions. Global CLAUDE.md and project AGENTS.md must be loaded into context in full — never summarized, truncated, or skipped.
digraph loader {
"Conversation starts" [shape=doublecircle];
"Agent handoff / context switch" [shape=doublecircle];
"Verify global CLAUDE.md" [shape=box];
"Load project AGENTS.md" [shape=box];
"Verify both loaded" [shape=diamond];
"Proceed with task" [shape=box];
"Reload missing file(s)" [shape=box];
"Conversation starts" -> "Verify global CLAUDE.md";
"Agent handoff / context switch" -> "Verify global CLAUDE.md";
"Verify global CLAUDE.md" -> "Load project AGENTS.md";
"Load project AGENTS.md" -> "Verify both loaded";
"Verify both loaded" -> "Proceed with task" [label="yes"];
"Verify both loaded" -> "Reload missing file(s)" [label="no"];
"Reload missing file(s)" -> "Verify both loaded";
}
Global CLAUDE.md (~/.claude/CLAUDE.md) is auto-loaded by Claude Code into system context. Verify it's present — if the canary instruction response is missing, warn the user: "Global CLAUDE.md not detected in context."
Do NOT re-read this file if it's already in context — that wastes tokens.
Read the project's AGENTS.md in full:
After loading, confirm both are in context:
Re-verify and reload if necessary when ANY of these occur:
npx claudepluginhub necturalabs/agentskills --plugin necturalabsAutomatically discovers and loads AGENTS.md files across project hierarchy and subdirs, merges instructions hierarchically for AI agent context, reports conflicts, caches results.
Initializes or migrates a project to nested CLAUDE.md files for progressive disclosure. Splits bloated root config into topic-specific docs/agents/ files.
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files for repos using empirical best practices. Triggers on /init, create/update requests, or missing context during brainstorming.