Skip to content

nanocoai/nanoclaw / .claude/skills/add-ollama-tool

add-ollama-tool

Verified

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

FileKindSize
REMOVE.mdmarkdown1.7 KB
SKILL.mdskill md11.8 KB
ollama-env.tsscript958 B
ollama-mcp-stdio.tsscript13.7 KB
ollama-registration.test.tsscript2.2 KB
ollama-wiring.test.tsscript2.1 KB

ollama-env.ts

View on GitHub
/**
 * Host-side env forwarding for the Ollama MCP tool: any `OLLAMA_*` host
 * overrides, as spec-shaped env (a record) — argv never crosses composition
 * anymore.
 *
 * Ollama is local and keyless — these are configuration, not credentials:
 * `OLLAMA_HOST` is the base URL of the host's Ollama daemon, and
 * `OLLAMA_ADMIN_TOOLS` is the opt-in flag for the library-management tools.
 * Neither is credential-named, so the reach-in spreads this into the composed
 * `env` literal in `composeSessionSpec`.
 *
 * Lives in its own file so the reach-in in `container-runner.ts` is a single
 * spread and this logic is behavior-testable in isolation.
 */
export function ollamaEnv(): Record<string, string> {
  const env: Record<string, string> = {};
  if (process.env.OLLAMA_HOST) {
    env.OLLAMA_HOST = process.env.OLLAMA_HOST;
  }
  if (process.env.OLLAMA_ADMIN_TOOLS) {
    env.OLLAMA_ADMIN_TOOLS = process.env.OLLAMA_ADMIN_TOOLS;
  }
  return env;
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall