Skip to content

nanocoai/nanoclaw / .claude/skills/add-cursor

add-cursor

Flagged

Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).

payload/container/agent-runner/src/providers/cursor-hook.ts

View on GitHub
/**
 * Cursor sessionStart / preCompact hook adapter.
 *
 * Cursor hooks speak JSON on stdin/stdout. NanoClaw's shared memory hook
 * prints plain text. This wrapper maps Cursor's lifecycle events onto
 * `memoryContextForSessionStart`. sessionStart takes `additional_context`.
 * preCompact only forwards `user_message`, so compact returns that field.
 *
 * Invoked as: `bun /app/src/providers/cursor-hook.ts` (sessionStart)
 *         or: `bun /app/src/providers/cursor-hook.ts --compact` (preCompact)
 */
import fs from 'fs';

import { memoryContextForSessionStart, type MemorySessionStartSource } from '../memory/session-hook.js';

export function resolveSource(argv: string[], stdin: string): MemorySessionStartSource {
  if (argv.includes('--compact')) return 'compact';
  try {
    const parsed: unknown = JSON.parse(stdin);
    if (parsed && typeof parsed === 'object' && 'source' in parsed) {
      const source = (parsed as { source?: unknown }).source;
      if (source === 'compact' || source === 'clear' || source === 'startup' || source === 'resume') {
        return source;
      }
    }
  } catch {
    /* Cursor sessionStart has no `source` field — treat as a new window. */
  }
  return 'startup';
}

export function hookPayload(
  source: MemorySessionStartSource,
  baseDir?: string,
): { additional_context?: string; user_message?: string } {
  const context = memoryContextForSessionStart(source, baseDir);
  if (!context) return {};
  // Cursor's preCompact response copies only user_message into the compaction
  // request. additional_context is the sessionStart field and is dropped here.
  if (source === 'compact') return { user_message: context };
  return { additional_context: context };
}

function readStdin(): string {
  try {
    return fs.readFileSync(0, 'utf-8');
  } catch {
    return '';
  }
}

if (import.meta.main) {
  const source = resolveSource(process.argv.slice(2), readStdin());
  process.stdout.write(JSON.stringify(hookPayload(source)) + '\n');
}
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: 471kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall