Setup

Install-style flow that lays down the infrastructure OMCR needs to operate in a project. This is OMCR's analog of OMC's /omc-setup — no research-interview questions, no preset selection, no manuscript scaffolding. Just makes the plugin work.

After /omcr-setup completes, the user should run /start-research for interview-style first-project initialization.

When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.

Safe to re-run. Diffs against current state; only adds what is missing.

What this installs

1. CLAUDE.md infrastructure — ## Project context, ## Research stack, ## Language preference blocks with placeholder fields. (Filled in later by /start-research.)
2. Agent memory directories — .claude/agent-memory/<agent>/MEMORY.md for the 6 core agents, seeded from the canonical template. Existing files are never touched.
3. Bibliography files — empty paper/references.bib (with header comment) and references.csv (with header row) at default paths. Existing files are never touched.
4. Permission allowlist — curated .claude/settings.json so common research-flow tools (read-only git, file search, edits, LaTeX build, citation lookups, figure crop) don't prompt every time. Dangerous operations (git write, file deletion, wildcard bash) are intentionally excluded so they always prompt.

What this explicitly does NOT do