Flow sync status

Skill cofin/flow/skills/flow-sync-status

Context-Driven Development toolkit for AI agents — spec-first planning, TDD workflow, and Beads integration.

Install

npx -y skills add cofin/flow --skill flow-sync-status

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when syncing Beads state to markdown, checking Flow status, refreshing context docs, validating task markers, or reporting ready/blocked Flow work.

SKILL.md

2.6 KB, as published. Nobody here has run it

Flow Sync And Status

Use this lifecycle skill for status dashboards, sync, context refresh, cleanup checks, and drift reporting.

Beads mode: Skip every bd invocation when the SessionStart hook reports Beads Backend: Missing (None) or Disabled via plugin config (useBeads=false). With no backend, /flow:sync is a no-op (announce and exit) and status falls back to spec.md markers. Never halt for missing Beads. See ../flow/references/discipline.md.

Workflow

Read .agents/beads.json before any sync/export decision.
Pull Beads state and notes as the source of truth.
Regenerate synchronized markdown views without changing requirement text.
Detect drift in workflow commands, tech stack, patterns, knowledge chapters, and references.
Report ready, blocked, in-progress, and stale work with clear next actions.

Guardrails

/flow:sync ALWAYS writes the reconciled markdown to disk. It is mandatory: regenerate every markdown file in .agents/specs/<flow_id>/ (spec.md, learnings.md, and any other tracked markdown in the flow folder) — not just spec.md — so they all match Beads exactly, and persist them. Sync is never read-only/dry-run and must never finish without writing the markdown.
"Sync"/"export" means reconciling markdown ↔ Beads to identical reality on disk — NOT Dolt. NEVER run bd dolt push/bd dolt pull (Dolt remote sync) or bd export (the optional JSONL snapshot) as part of sync. They are out of scope and only run if the user explicitly and separately asks for them.
Sync reads backend state; do not close, block, or mutate tasks during status reporting.
Do not auto-stage/commit unless policy or the user explicitly allows it.
Preserve human-written spec content; only update synchronized task/status regions.
Ask before applying context-doc updates when sync detects drift.

Validation

Confirm status comes from Beads, not markdown markers.
Confirm broken file references, workflow drift, and sync policy decisions are reported.
For this repo, run make validate-skills after skill or command sync changes.

References Index

Example

User: "Flow status."

Action: read Beads state, summarize active flows, ready tasks, blockers, recent notes, and whether markdown views need sync.