A Claude Code plugin for a structured dev workflow — 14 expert agents, code review, planning, and task tracking, all from the terminal.
Command
Ask a question about the outside world, get back a concise answer where every non-trivial claim carries a citation — searched and fetched from the live web, cross-checked by a skeptic agent, and honestly labeled where the evidence is thin.
Command
Ask a single expert agent a question - like a Slack ping to a colleague.
Command
Backlog review and cleanup - multi-agent backlog review, quick no-agent pulse (--fast), or interactive triage cleanup.
Command
Quick sanity check - code (inline 6-perspective) or plan (--plan).
Command
Finish a task - document, create PR or merge, close.
Command
End a work session - a settlement pass that reconciles uncommitted / unpushed work + session context into git, the tracker, and a session snapshot file. --pre-compact skips settlement and only writes the shared snapshot, keeping the session going.
Command
Execute implementation plan from /lets:plan - load plan and enter native plan mode.
Command
GitHub PR review lifecycle - analyze, discuss, post inline comments, follow-up, respond, approve.
Command
Initialize LETS in current project - creates .lets/ structure, config, statusline, beads; offers user-scope global-rules install when the plugin is user-scoped.
Command
First-time global setup - install plugins, configure environment, explain workflow.
Command
Add a note to the active task - progress, decisions, context. --pre-compact writes a resume-grade session snapshot before /compact.
Command
Technical decision analysis from expert agents launched in parallel, with clear recommendation.
Command
PREVIEW (experimental) - autonomous /lets:plan via a Dynamic Workflow. Shipped standalone to dogfood across projects and gather edits before folding the chain into native /lets:plan.
Command
Structured planning - explore codebase, design architecture, evaluate options, produce detailed implementation plan.
Command
Generate a self-contained hand-off brief so ANOTHER agent (a fresh session, Codex, any external reviewer) can pick up the exact state and review it - a plan, a branch, the last commits, a PR, or one file. Produces one pasteable brief; reviews nothing itself.
Command
Work through a RECEIVED round of review comments (inline markers, a review file, or PR threads) on a spec/doc/PR. Triage each item, record decisions to the tracker task, keep the artifact FROZEN, then apply all edits in ONE final pass. Use when a reviewer returns N comments to incorporate.
Command
Full code review with dynamic agent selection (up to 12 specialized agents). Analyzes changes first, selects relevant experts. Also reviews implementation plans.
Command
Start session - restore context, show tasks, select work item.
Command
Read-only orientation snapshot - where you are, what's in flight, what's next (tracker-universal).
Command
Manage & persist statusline appearance - light/dark, compact, and which rows to show.
Command
Parallel implementation with Agent Teams - spawn teammates in isolated worktrees.
Command
Sync this project with the current LETS release - a self-driving one-step loop; self-heals .env + rules (rules deferred while the plugin is behind), installs the binary in-session on approval, and points at the single next action until everything is on the same version.
Command
Worktree lifecycle management - create, list, remove, info on interactive worktrees.