watt-mind

watt-mind/factory

Agent

Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.

watt-mind/factory

Agent

You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.

watt-mind/factory

Agent

Return the supplied message unchanged.

watt-mind/factory

Agent

Return a friendly greeting using the supplied name.

watt-mind/factory

Agent

Assess the supplied disk observation. Explain the current capacity, identify the most urgent non-destructive follow-up, and never execute a command or modify a host.

watt-mind/factory

Plugin Claude Code

Watt Mind execution protocol: dispatch, review/merge, triage, and conventions audit.

watt-mind/factory

Agent

Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…

watt-mind/factory

Agent

Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…

watt-mind/factory

Agent

Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…

watt-mind/factory

Agent

End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…

watt-mind/factory

Command

Audit this repo against the project-conventions baseline; file the gaps to Linear.

watt-mind/factory

Command

File a Linear issue from this conversation, per the ai:agent-ready protocol — capture only, never implement.

watt-mind/factory

Command

File harness friction observed in an interactive session — capture only, never implement.

watt-mind/factory

Command

Review open PRs thoroughly, fix what's fixable, merge what's good.

watt-mind/factory

Command

Recommend and optionally run the next factory stage for this repo.

watt-mind/factory

Command

Linear status report across configured repos — queue depth, triage backlog, ready-to-dispatch, blocked/held.

watt-mind/factory

Command

Find what is repeatedly wasting the factory's time and fix the harness, not the symptom.

watt-mind/factory

Command

Release — open a develop → master PR, wait for CI, merge, verify the deploy.

watt-mind/factory

Command

Find Linear tickets that have gone obsolete (duplicate, already shipped, overtaken by events) and retire them with evidence.

watt-mind/factory

Command

Implement exactly one already-claimed Linear ticket in the current worktree.

watt-mind/factory

Command

Find open Linear issues for this repo and triage them toward agent-ready.

watt-mind/factory

Command

Re-examine held (ai:blocked) tickets for new evidence and release the ones that no longer need a human.

watt-mind/factory

Command

Dispatch subagents to work agent-ready Linear tickets, land the PRs, report.