Lw Docs Sync — Development agent for Claude Code
Runs the leanwheel docs-sync skill (OPERATIONAL or PROMOTE op) in an isolated, low-cost context.
How to install Lw Docs Sync
Installs to ~/.claude/agents/rterakedis-leanwheel-skills-lw-docs-sync.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rterakedis/leanwheel-skills/HEAD/agents/lw-docs-sync.md -o ~/.claude/agents/rterakedis-leanwheel-skills-lw-docs-sync.md Restart Claude Code, or start a new session, for it to be picked up.
What Lw Docs Sync does
name: lw-docs-sync description: Runs the leanwheel docs-sync skill (OPERATIONAL or PROMOTE op) in an isolated, low-cost context. Spawned by the flywheels after a dev phase (OPERATIONAL) and at the epic boundary / retrospective (PROMOTE), and usable by any main-session caller that wants documentation maintenance off the expensive model. Pinned to Haiku — this is mechanical, grounded-in-diff doc writing, never reasoning-heavy. model: haiku effort: low
You are the leanwheel **docs-sync run
Alternatives in Development
- Liveops Manager — Owns live events, offers, telemetry-informed updates, and post-launch operational planning 76 ★
- Issue Maintainer — Use when filing, closing, triaging, or structuring issues/epics on your git host — it owns issue/epic STRUCTUR 71 ★
- Reply Handler — Sync and classify campaign replies using 3-tier cost-optimized funnel 66 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Lw Story Reviewer
Runs the leanwheel code-review workflow adversarially on a story's diff in an isolated context. Spawned by /st
Unit Economist
Use when validating C3 (custo ≤ 25% do preço), reviewing baseline-cost.md, auditing recalc_unit_economics_requ
Epic Atdd Writer
Generates FAILING acceptance tests (TDD RED phase). Use ONLY for Phase 3. Isolated from implementation knowled
Retrospective Agent
Daily / weekly / monthly self-improvement retrospective. Reads the auto-generated dev-log digests (docs/dev-lo
Mb Reviewer Scalability
Performance/scalability reviewer for Memory Bank governed review ensembles. Focuses on complexity, hot paths,
Operational Readiness
Assesses the ongoing human cost of the proposed feature — support burden, moderation/ops staffing, maintenance
Related Skills
Claude Memory Kit
Memory for Claude Code that survives the session boundary — install the plugin into any repo: a hot cache inje
Boundary Assumption Verification 20260801
Mandating explicit documentation and verification of foundational operational assumptions at process boundarie
Claude Improve
A self-improving retrospective skill for Claude Code. One command makes your AI agents get better after every