executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
hyperflow-scaffoldHyperflow project setup. Use when starting hyperflow in a new project or refreshing its cache — "init hyperflow", "set up hyperflow", "refresh hyperflow", "scaffold hyperflow". One-shot setup of the .hyperflow/ project cache + memory and the .agent/workflows/hyperflow* slash commands. Does not start the plan → dispatch chain.
Independent GitHub snapshot · Automated classification · Original documentation governs
One-shot setup of hyperflow's project surfaces. Follow the hyperflow doctrine.
.hyperflow/ cache at the repo root if absent:
.hyperflow/memory/ with decisions.md, learnings.md, pitfalls.md, patterns.md (empty stubs, each with a one-line header)..hyperflow/tasks/, .hyperflow/specs/, .hyperflow/audits/ (empty dirs)..hyperflow/profile.md, architecture.md, conventions.md) by reading the repo: stack, top-level layout, test/lint conventions, commit conventions. Keep each short and factual.hyperflow* workflow files into <repo>/.agent/workflows/ (so /hyperflow, /hyperflow-plan, /hyperflow-design, … resolve in Antigravity's / menu). Source: the templates/antigravity/workflows/ shipped with hyperflow.~/.gemini/config/skills/ (auto-trigger) and global rules in ~/.gemini/AGENTS.md..hyperflow/ content; only create what's missing..hyperflow/tasks and .hyperflow/specs are runtime artefacts; .hyperflow/memory is durable and worth committing.