Agent.Gantry

Orchestrate a Gantry plan to a finished PR — Claude writes a goal-prompt doc, delegates implementation stages to the Codex plugin (xhigh + ponytail), verifies and commits between stages, and closes with the autoreview loop. Use when the user asks to implement a plan/goal prompt, "run the goal pipeline", "same as the goal", or hands over a docs/architecture/*-goal-prompt.md to execute.

End-to-end Gantry plan implementation pipeline. Use when the user asks to implement or pursue a plan, goal prompt, feature, fix, refactor, PR update, or "same as the goal" workflow with subagent implementation, ponytail simplicity, no-commentary implementation, autoreview, build, launchctl restart, Knacklabs lead gen smoke, and PR/pipeline closeout.

Gantry self-administration reference for current host runtime operations: CLI commands, settings.yaml runtime settings, .env credential keys, agent management, scheduler tools, memory tools, browser tools, diagnostics, and service control. Use when asked to manage Gantry itself.

Guides Gantry tool, skill, MCP server, browser, local CLI, semantic capability, inventory, and permission lifecycle work. Use when changing durable capability selection, visible attached sources, transient request_permission flows, or agent access review paths.

Drives Gantry agent-chat tests through the local Control API session path and captures assistant responses. Use when testing an agent response, permission prompt, skill behavior, or runtime chat flow without needing Telegram UI rendering.

Use when creating or revising a Gantry product, UX, permission, job, ingress, provider, settings, or agent-flow plan that must be decision-complete with no room for assumptions. Triggers for PM plan, product manager plan, no assumptions, UX flow, user flow, agent flow, acceptance criteria, validation plan, provider-neutral plan, or Surface Impact Matrix.

Drives Gantry tests through the visible Telegram UI with Chrome. Use only when testing Telegram rendering, Telegram buttons, topic routing, or visible Telegram conversation behavior; use agent-chat-test for direct runtime agent-chat tests.

Use for folder movement, layer boundaries, and domain/application/runtime/adapters refactors in Gantry.

Enforces Gantry planning and handoff discipline for meaningful feature, fix, refactor, or replacement work. Use when a task needs a plan, Surface Impact Matrix, no-legacy cleanup evidence, verification selection, or PR-ready handoff.

Guides Gantry memory architecture work around session digest, continuity, compaction, dreaming, retrieval, source-first ingestion, and cleanup. Use when planning or changing memory services, generated memories, memory APIs, MCP tools, settings, or retrieval behavior.

Use for tools, permissions, risky actions, sandbox, browser, and execution safety changes in Gantry.

Use for LLM, channel, browser, sandbox, credential, and external provider adapter changes in Gantry.

Guides Gantry local runtime verification, build/restart/status workflows, launchd service checks, disposable Postgres testing, and release handoff. Use when asked to build, restart, validate runtime health, verify DB-backed behavior, or confirm what is actually running.

Guides Gantry autonomous job, scheduler execution, notification route, capability metadata, recovery, terminal evidence, and job visibility work. Use when changing scheduled jobs, run-now/readiness, job tool access, delivery recovery, or job status surfaces.

Use for Postgres schema, migrations, persistence repositories, and storage contract changes in Gantry.

Guides Gantry changes to settings.yaml desired state, settings projection, control API, CLI, Gantry MCP/admin tools, agents, conversations, model defaults, and provider connections. Use when changing configuration ownership or any settings-backed runtime surface.