con un clic
flywheel-healthcheck
Full health check of the codebase and flywheel dependencies.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Full health check of the codebase and flywheel dependencies.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | flywheel-healthcheck |
| description | Full health check of the codebase and flywheel dependencies. |
Run a health check. $ARGUMENTS
Produce a health score across dependencies, codebase state, and beads.
Dependency checks (run in parallel via Bash):
br --version — bead trackerbv --version — bead visualizercurl -s --max-time 3 http://127.0.0.1:8765/health/liveness — agent-mailgit status --short — repo cleanlinessls .pi-flywheel/checkpoint.json 2>/dev/null — checkpoint statels mcp-server/dist/server.js 2>/dev/null — MCP server builtCodebase health (use Agent(Explore)):
grep -r "TODO\|FIXME\|HACK" --include="*.ts" | wc -lBead health:
br list --json — count open/closed/in-progress/deferredbv --json — check for cycles or orphaned beadsDisplay health report:
DEPENDENCIES
✅ br v1.x.x
✅ bv v1.x.x
✅ agent-mail — healthy
⚠️ MCP server not built (run: cd mcp-server && npm run build)
CODEBASE
TODOs: N
Test coverage: N% (N test files / N source files)
Git: clean / N uncommitted changes
BEADS
Open: N | In progress: N | Closed: N | Deferred: N
Graph: ✅ no cycles | ⚠️ N orphans
HEALTH SCORE: N/10
Healthcheck is the third of three diagnostic commands. Run them in order:
/agent-flywheel:flywheel-doctor — read-only snapshot. Run first when toolchain drift is suspected./agent-flywheel:flywheel-setup — apply-fixes stage; installs tools, registers MCP, configures hooks./agent-flywheel:flywheel-healthcheck (this skill) — deep periodic audit of codebase, bead graph, and dependencies. Run it on a cadence, not for fresh-clone setup problems (use doctor → setup for that).Relentless goal/design interview that sharpens framing and writes durable docs (brainstorm artifact, ADRs, glossary) as decisions crystallize. Use when refining a flywheel goal, pressure-testing scope, or "grill with docs".
Start or resume the full agentic coding flywheel. Drives the complete workflow: scan → discover → plan → implement → review.
Set up flywheel prerequisites for this project.
One-shot diagnostic of every flywheel dependency — MCP connectivity, Agent Mail liveness, br/bv/ntm/cm binaries, node version, git status, dist-drift, orphaned worktrees, and checkpoint validity. Use when debugging toolchain issues, before starting a new session, after /flywheel-cleanup, or as a CI gate.
Strategic gap analysis between vision (AGENTS.md / README.md / plan docs) and what's actually implemented. Converts gaps into beads, optionally launches a swarm. Use when "reality check", "where are we really", "gap analysis", "did we drift", or before declaring a long-running project done.
Launch a parallel swarm of agents to implement multiple beads simultaneously.