snipara-companion

snipara-companionis Snipara's optional local helper CLI for hook-oriented automation workflows. It complements snipara-mcp; it does not replace it.

When to use it

• You want a local helper CLI around hook-oriented workflows.
• You are targeting clients like Claude Code, Cursor, or Windsurf.
• You want the installed rlm-hook command for local automation steps.
• You want automatic routing from natural-language structural queries into rlm_code_* tools.

When not to use it

• Do not install it just to get Snipara MCP. Use snipara-mcp for that.
• Do not install it by default for Codex. Codex works with mcp.json and AGENTS.md.
• Do not treat it as the same thing as snipara-orchestrator or snipara-openclaw-hooks.

Install

npm install -g snipara-companion

The installed executable is rlm-hook.

What it adds now

• Auto-follow structural recommendations: rlm-hook query --follow-recommendation will execute the recommended rlm_code_* tool when Snipara detects a structural code question.
• Workflow presets: rlm-hook workflow run --mode auto and --mode full combine retrieval, planning, and graph follow-up.
• Runtime hints: workflow runs suggest RLM Runtime for FULL, orchestrated, or execution-heavy work without executing Runtime jobs themselves.
• Local readiness check: rlm-hook doctor reports Snipara auth, RLM Runtime CLI, Runtime MCP config, provider keys, and Docker.
• Direct code graph access: rlm-hook code callers, imports, neighbors, and shortest-path.
• Project-linked standards on demand: rlm-hook shared-context loads the shared collections linked to the current project instead of preloading every team rule on every session.

Quick start

rlm-hook init --with-hooks --client claude-code

rlm-hook query --query "who calls src.rlm_engine.RLMEngine._handle_context_query" --follow-recommendation

rlm-hook workflow run --mode full --query "plan the auth refactor"

rlm-hook workflow run --mode full --no-runtime-hint --query "plan the auth refactor"

rlm-hook doctor

rlm-hook code imports --file-path src/rlm_engine.py

rlm-hook shared-context --categories BEST_PRACTICES GUIDELINES

Context hierarchy

• Project context first: companion stays scoped to the current workspace and project when it runs retrieval.
• Shared context through the project: team standards are pulled from the shared collections linked to that project, not from every collection in the team.
• No global team preload: reviewed memory and workspace defaults preload at session start; shared/team context is fetched when the task actually asks for standards, conventions, or compliance guidance.

Supported presets today

• claude-code
• cursor
• windsurf

Companion vs other packages

Should companion and orchestrator merge?

No. snipara-companion is a local npm CLI centered on hook workflows and local automation ergonomics. snipara-orchestrator is a Python package for advanced production validation and orchestration. Merging them would make install guidance and product positioning less clear, not more.

Recommended split

• Use snipara-companion for day-to-day development flow, hook automation, code graph routing, and lightweight workflow presets.
• Add RLM Runtime when the workflow needs local execution, tests, lint, or sandboxed validation. Companion can suggest Runtime and diagnose local readiness, but Runtime remains a separate execution layer.
• Reach for snipara-orchestrator only when you need proof-based validation, drift detection, or production gates.

Related guides

• Which Package?
• Orchestrator guide
• OpenClaw guide