The factory loop's companion, enabled beside factory-loop: starts each agent the loop runs in its worktree slot, confines its writes and pushes, gives its commands a 10-minute timeout, and holds a writer's finish while the repo's gates fail.
2 on GitHubby Callum Bundyv0.101.2updated 16 days ago
/
Plugin factory-loop-workspace from marketplace callum in cbundy/dev-system. Commands read from the repo's manifest — 14 days ago.
What it installs
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
The old name of fabriek, the same plugin, kept as a second marketplace name for the 10-minor-release window so a workspace whose settings still enable callum-flow@callum keeps its guard hooks. Install only one of the two.
Skills (update-dev, onboard, evaluate-sessions, query-factory-data, factory-state, backlog-triage, dependency-chain) and hooks for working in a dev-system repo.
The issue orchestrator as a deterministic loop: claims, gates and merges a repo's ready issues in code and wakes Claude only for judgment calls. For orchestrator workspaces (the orchestrator-loop Coder template); not enabled by default.
Opt-in mod: a status entry with the time, context fill, plan usage, factory counts and tool versions on every surface, including mobile and desktop through Remote Control.
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.