lets

Plugin lets from marketplace lets-workflow in restarter/lets-workflow. Commands read from the repo's manifest — yesterday.

Skills (20)

• actor-fetch-personality

  Internal skill for commands. Fetch and validate personality from URL or file path for Actor agent. Do not trigger on user conversation - only when commands need personality loading.

• agent-report

  Internal skill for commands. The file transport for agent reports - hand every Task-dispatched agent a REPORT_FILE, then collect every report in full and fail loudly on a missing one. Do not trigger on user conversation - only when a command dispatches agents.

• apply-fixes

  Internal skill for commands. Apply a review's verified fixes to the working tree when nothing needs deciding - the --fix flag of /lets:check, /lets:review and /lets:handoff, and the final pass of /lets:review-round. Do not trigger on user conversation - only when one of those commands runs with --fi

• artifact-path

  Internal skill for commands. Resolve a unique, task-scoped, collision-safe path for an artifact written under .lets/ (plans, reviews, session snapshots, hand-off briefs, per-run agent report directories). Do not trigger on user conversation - only when a command is about to write an artifact.

• backlog-workflow

  Dynamic Workflow asset for /lets:backlog review --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:backlog. Holds the off-context ideate -> cluster fan-out over the backlog.

• commit

  This skill should be used when committing code changes - "commit", "git commit", "закоміть", "зроби коміт", "/lets:commit". Enforces conventional commit format, tracker task linking, and the gate level (`LETS_GATES`). In a LETS project, ALWAYS prefer this over generic commit skills (e.g. commit-comm

• create-task

  This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context

• detect-task

  Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.

• member-run

  Internal skill for commands. Spawn, hand the next brief to, correct, dismiss or wait for the round report of ONE named member - any lets:* role - of a team or an execute run; the caller's record (the execute run record, the team file) is the record, and ListAgents judges who is busy. It is the singl

• opinion-workflow

  Internal Dynamic Workflow asset for /lets:opinion --workflow. Not auto-triggered - it is a workflow script invoked via scriptPath, not a conversational skill. Holds the fan-out -> tally -> conditional-challenge -> synthesize chain that runs off-context.

• orc

  This skill should be used when the user wants to talk to another LETS session of this repo - "ask the orchestrator", "ping the orchestrator", "what did the orchestrator say", "who is working", "message <name>", "tell <name>", "спитай у оркестратора", "запінгуй оркестратора", "що там оркестратор писа

• orient

  Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.

• plan-workflow

  PREVIEW Dynamic Workflow asset behind /lets:plan-workflow. Not auto-triggered - a workflow script invoked via scriptPath. The autonomous-planning chain, shipped for cross-project testing before it folds into native /lets:plan.

• protocol-orchestrator-offer

  Internal skill for commands. The Orchestrator offer protocol - when a command touchpoint offers the orc skill to ask this session's orchestrator, how the target is resolved once per run, and the Act and Nav offer shapes. Loaded by a command right before its first selected touchpoint. Do not trigger

• protocol-tracker

  Internal skill for commands. The tracker verb-resolution protocol - how a lets-tracker block resolves through the active adapter, the neutral read shape, body crossing, degradation, preflight and trust. Loaded by a command or skill right before its first tracker verb. Do not trigger on user conversa

• research-workflow

  Dynamic Workflow asset for /lets:research --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:research. Holds the off-context per-sub-question web research -> per-claim skeptic cross-check -> synthesize chain.

• review-workflow

  Internal Dynamic Workflow asset for /lets:review --workflow. Not auto-triggered - it is a workflow script invoked via scriptPath, not a conversational skill. Holds the fan-out -> dedupe -> adversarial-verify -> aggregate chain that runs off-context.

• session-boundary

  Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.

• session-snapshot

  Internal skill for commands. Write a recovery-grade session snapshot (file-primary) for /lets:end and for the --session snapshot-only flag of /lets:end and /lets:note. Always writes a .lets/sessions/ file; adds a one-line task pointer only when a task is unambiguously active. Do not trigger on user

• take-task

  This skill should be used when claiming a task to work on - "take task", "візьми таск", "працюю над", "work on task X", "pick task X", "switch to task X", "claim task". Sets task to in_progress, creates/switches branch, saves the per-branch task-state file.

Slash commands (26)

• /lets:ask

  Ask a single expert agent a question - like a Slack ping to a colleague

• /lets:backlog

  Backlog review and cleanup - multi-agent backlog review, quick no-agent pulse (--fast), or interactive triage cleanup

• /lets:check

  Quick sanity check - code (inline 6-perspective) or plan (--plan).

• /lets:done

  Finish a task - document, create PR or merge, close

• /lets:end

  End a work session - a settlement pass that reconciles uncommitted / unpushed work + session context into git, the tracker, and a session snapshot file. --session (aliases --snapshot, --pre-compact, --compact) skips settlement and only writes the shared snapshot, keeping the session going.

• /lets:execute

  Execute implementation plan from /lets:plan - inline in native plan mode, or delegated to named implementer subagents you review and correct

• /lets:github-pr

  GitHub PR review lifecycle - analyze, discuss, post inline comments, follow-up, respond, approve

• /lets:handoff

  Generate a self-contained hand-off brief so ANOTHER agent (a fresh session, Codex, Antigravity, any external reviewer) can pick up the exact state and review it - a plan, a branch, the last commits, a PR, or one file - or implement an approved plan (--execute). Prints one pasteable brief, or deliver

• /lets:hub

  Cross-project hub on Orca - see every project's orchestrators, ask a stopped one read-only, wake one for gated work (Orca addon)

• /lets:init

  Initialize LETS in current project - creates .lets/ structure, config, statusline, beads; offers user-scope global-rules install when the plugin is user-scoped

• /lets:install-deprecated

  First-time global setup - install plugins, configure environment, explain workflow

• /lets:note

  Add a note to the active task - progress, decisions, context. --session (aliases --snapshot, --pre-compact, --compact) writes a resume-grade session snapshot without ending the session. --team writes a fact or a decision into the standing team's file.

• /lets:opinion

  Technical decision analysis from expert agents launched in parallel, with clear recommendation

• /lets:peer

  Talk to a named LETS peer session (alias of /lets:orc with a target)

• /lets:plan-workflow

  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.

• /lets:plan

  Structured planning - explore codebase, design architecture, evaluate options, produce detailed implementation plan

• /lets:research

  Answer an external or technical question by searching the web and synthesizing a CITED answer, with a cross-check pass that flags weak or contradicted claims

• /lets:review-handoff

  (deprecated) Alias of /lets:handoff - the old name, removed in a future release; self-contained hand-off brief for another agent, optionally delivered with --send, --open or --codex

• /lets:review-round

  Work through a RECEIVED round of review comments - inline markers, a review file, a saved /lets:review or /lets:handoff report, the items --fix left needing a decision, PR threads - on a spec, doc or PR. Triage each item, record each decision on its own task, keep the artifact FROZEN, apply all edit

• /lets:review

  Full code review with dynamic agent selection (up to 12 specialized agents). Analyzes changes first, selects relevant experts. Also reviews implementation plans.

• /lets:start

  Start session - restore context, show tasks, select work item

• /lets:status

  Read-only orientation snapshot - where you are, what's in flight, what's next (tracker-universal)

• /lets:statusline

  Manage & persist statusline appearance - light/dark, compact, and which rows to show

• /lets:team

  Team management - run several tasks at once, one visible LETS session per task on any launcher

• /lets:update

  Sync this project with the current LETS release - a self-driving one-step loop; self-heals .env + project rules (rules deferred while the plugin is behind), reports the hook-maintained global rules, installs the binary and refreshes the plugin in-session on approval, and points at the single next ac

• /lets:worktree

  Worktree lifecycle management - create, list, remove, info on interactive worktrees

Subagents (15)

• actor

  Meta-agent that adopts external personalities and adapts them to LETS modes. Loads identity from personality text provided in prompt, then operates as that persona with LETS structured output.

• architect

  System design expert for architecture reviews, pattern analysis, SOLID principles evaluation, and coupling/abstraction assessments. Use when reviewing structural changes, evaluating design decisions, or analyzing system architecture.

• backend

  Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

• compliance

  Project standards expert for CLAUDE.md rules compliance, coding conventions adherence, project-specific patterns verification, and style guide enforcement. Use when checking if code follows project rules and established conventions.

• database

  Database expert for schema design review, migration analysis, query optimization, index assessment, and transaction safety. Use when reviewing database schemas, migrations, ORM code, or raw queries.

• devops

  DevOps and infrastructure expert for Docker review, CI/CD pipeline analysis, deployment configuration, shell script assessment, and infrastructure-as-code evaluation. Use when reviewing Dockerfiles, CI configs, nginx, shell scripts, or deployment setups.

• docs

  Documentation expert for API docs review, README assessment, inline documentation analysis, and changelog evaluation. Use when reviewing documentation quality, checking docs-code sync, or evaluating developer onboarding materials.

• explorer

  Codebase cartographer for mapping structure, patterns, and integration points relevant to a proposed feature. Use during planning to understand what exists before designing what to add.

• frontend

  Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.

• git-historian

  Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.

• implementer

  Full-stack implementation specialist. Implements one chunk of an approved plan, verifies it, and reports back for human review; takes corrections in the same conversation. Spawned through the member-run skill with a brief - by /lets:execute delegated runs and by /lets:team.

• pragmatist

  Pragmatic ROI analyst for overengineering detection, effort-vs-value assessment, scope creep identification, and "good enough" evaluation. Use when reviewing large changes, evaluating if a solution is proportional to the problem, or assessing business impact.

• qa

  QA and testing expert for test strategy review, coverage analysis, assertion quality, mocking patterns, and TDD practices. Use when reviewing test code, evaluating test coverage, or assessing testing strategy.

• security

  Security specialist for vulnerability detection, auth review, crypto assessment, secrets scanning, and input validation analysis. Use when reviewing security-sensitive code, auth flows, data handling, or API endpoints.

• skeptic

  Adversarial verifier for one or more review findings, each judged on its own; or, in CHECK mode, a quick check you run and then verify. Given claimed issues plus the code, tries to refute each against reality to cut false positives. Use to verify findings before they are reported. Read-only. Also cr

Hooks (1)

• SessionStart

  lets hook session-start --rules=${CLAUDE_PLUGIN_ROOT}/rules/lets-rules.md

Similar plugins