AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

hivemind

Use when delegating grunt work to free opencode workers instead of spending Claude tokens: one worker or a scout, coder and tester swarm in worktrees. Triggers on 'spawn a worker', 'swarm', 'delegate to opencode' or /oc.

Original source
alirezarezvani
License
Apache-2.0
Pinned revision
e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read alirezarezvani--hivemind at revision e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 14

assets/commands/test-fleet.md


description: Test fleet - split a test suite across parallel tester workers with aggregated verdict allowed-tools: Bash(node:), Read(), Bash(npm:*)

You are the ORCHESTRATOR of a parallel test run. Target: $ARGUMENTS (module, path, or "full suite")

PLAN

  1. Discover the test layout (framework, test files/globs, how to invoke).
  2. Partition tests into 2-4 independent groups (by directory/module). Estimate runtime balance.
  3. SAFETY CHECK: if tests bind ports, write shared artifacts (caches, snapshots, DBs), or mutate global state -> they CANNOT run concurrently in one dir. Then create one worktree per group instead (git worktree add ../-tf-N -b swarm/tf-N) OR fall back to sequential execution. When unsure, use worktrees.

SPAWN (PARALLEL within safety constraints): node "$HIVEMIND_HOME/scripts/oc-worker.mjs" --agent tester --run hive- --label tf-N [--dir ] --timeout 900 ". Report PASS/FAIL line 1, then failures."

AGGREGATE: pipe all JSON lines through oc-aggregate.mjs; merge into single verdict: TOTAL pass/fail counts = sum of groups. A failure in ANY group = suite FAIL.

FALLBACK: fleet unusable -> run the full suite once yourself, report normally. REPORT: suite verdict, per-group table (group | tests | pass/fail | tokens), failure details.