Agent
Central visual-verification agent. Deployed per request by the main-process verification scheduler in an isolated snapshot worktree; builds and serves the deliverable, drives the composed behaviors, captures screenshots, and returns a structured verification report. Never writes cyboflow state.
Agent
Sprint test-author subagent. Adds unit/integration tests covering the new diff and runs them; bootstraps a minimal runner when the project has none, or skips loudly with a machine-readable outcome. Never writes cyboflow state.
Agent
Verify Setup subagent. Surveys a project for how its UI actually stands up (scripts, framework, Electron vs web, isolation levers, existing runbook), then drafts a portable verification runbook per modality with a required attestation channel, machine-local bindings, and the lowest-rung repo changes that make it work.…
Plugin Claude Code
Plugin marketplace listing 2 plugins: soloflow, soloflow-dev.
Plugin Claude Code
Hooks-based workflow orchestration for solo product development with Claude Code.
Instructions file
Instructions for kesteva/soloflow, covering claude.md, project overview, constraints every agent must know, release / branch hygiene and reference.
Agent
Investigates a bug report — performs read-only root-cause analysis and produces a structured fix plan. Does NOT modify code.
Agent
Reviews CLAUDE.md improvement proposals against the existing codebase and CLAUDE.md files, producing tightly scoped diffs at the lowest appropriate directory level.
Agent
Reviews all CLAUDE.md files for focus, trims redundancy, and identifies content that should be moved to specialized reference files.
Agent
Reviews completed code for quality, reuse, and security.
Agent
Reviews a codebase for redundancy, inefficiency, orphaned code, and dead exports, then produces a structured pruning proposal.
Agent
Skeptical second-pass reviewer of a compound proposal; emits per-item IMPLEMENT / DONTIMPLEMENT verdicts with concrete evidence. Read-only except for the proposal file where it inserts verdict blocks.
Agent
Analyzes completed sprints and out-of-scope findings, then produces a three-bucket proposal (clean-ups, backlog tasks, CLAUDE.md / CODE-PATTERNS.md improvements) for the user to approve.
Agent
Implements a single task from an execution-ready plan with scope boundaries, deviation rules, and atomic commits.
Agent
Extracts and structures raw ideas, feature requests, and bug reports into actionable task specs.
Agent
Runs end-of-sprint integration and E2E tests, classifies failures as regressions or pre-existing.
Agent
Synthesizes a roadmap brief and research into a phased set of epics with dependencies, milestones, and success signals.
Agent
Gathers sprint close context and executes sprint close (mark complete, archive, commit, merge run branch) for the executor orchestrator.
Agent
End-of-sprint aggregate code reviewer; surfaces cross-task quality and security findings as queued findings for the compounder.
Agent
Gathers sprint context and executes sprint setup (branch, sprint.json, smoke tests) for the executor orchestrator.
Agent
Decomposes an approved idea into a coarse task skeleton (DAG, epic decisions, file-ownership hints) for downstream parallel detailers.
Agent
Refines approved ideas into execution-ready plans with acceptance criteria, file ownership, and dependency mapping.
Agent
Writes or updates unit and component tests for a single completed task's changes.
Command
Quickly capture multiple ideas and tasks from a braindump session.