Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
Agent Claude Code
Read-only adversarial contract reviewer. Reviews the full contract set against user scope, inventory, playbook rules, evidence feasibility, shortcut risk, and old-harness-style atomic assertion coverage before tasks are trusted.
Agent Claude Code
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
Agent Claude Code
Leaf real-surface validation lane for a bounded subset of engineering assertions. Exercises assigned behavior through a parent-specified browser, API, CLI, background, artifact, data, library, parity, or caller-provided tool surface; writes evidence only to assigned paths.
Agent Claude Code
Universal read-only investigation subagent for bounded evidence gathering: code reading, flow tracing, repo search, docs lookup, enumeration, coverage checks, decomposition review, and other context-preserving research. Returns cited findings for the parent to synthesize.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: