litisaude-garage

Plugin litisaude-garage from marketplace cascade-ai-ml-agents-misc-1 in joshuarweaver/cascade-ai-ml-agents-misc-1. Commands read from the repo's manifest — 1 month ago.

Skills (6)

• brief

  Turn a rough ask into a review-gated brief — the contract artifact the rest of the garage harness executes. Produces docs/specs/<slug>.md with a goal, house rules, a measurable Done Bar, workstream specs, and user-testable merge checkpoints; consults the advisor before the gate and loops the plan re

• orchestration

  Routing doctrine for the architect-as-orchestrator pattern — how a session running the smartest model delegates implementation to cheaper, cross-vendor, or workstream lanes to minimize cost while gating quality with fresh-context judges. USE WHEN delegating implementation work, choosing between impl

• parallel-feature

  execute a spec/plan across parallel workstreams — worktree-isolated subagents, one PR each, gated on CodeRabbit approval plus the garage review gate.

• review

  Composite review — fan out reviewer agents over a plan (requirements checklist) or code changes (violation report), merge into a single report with a machine-parsed VERDICT line.

• spec-writing

  Write or revise any spec, plan, brief, or design doc using ASD-STE100 Simplified Technical English writing rules plus a precision bar ("a sufficiently detailed spec is code"). Produces prose that non-native speakers and LLM implementers parse reliably, and content precise enough that the implementer

• visualize-plan

  Generate a "visual companion" for one or more PRD/TRD markdown files. Long specs become a multi-page mini-site with a sticky side menu (folder of self-contained HTML files); short specs become a single-page HTML. Both follow the Liti mobile design system and a fixed page-shell template so visuals st

Subagents (12)

• advisor

  Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — before architectural decisions, data migrations, big refactors, or API designs, and whenever the same problem has resisted two attempts. In the garage harness it is consulted by /brief before the

• analytics-coverage-reviewer
• audit-compliance-reviewer
• bar-judge

  Fresh-context adversarial judge. Given a written Done Bar and a pointer to the real output (a repo, a branch, a PR, a running app), it tries to PROVE the output fails the bar — running the bar's own verification commands and exercising the behavior. Returns a machine-parsed BAR VERDICT with evidence

• business-readiness-reviewer
• codex-implementer

  Cross-vendor implementation lane running GPT-5.5 via the OpenAI Codex CLI (`codex exec`, reasoning effort high). Route work here when correctness or completeness is critical enough to justify a second model family, or when you want an independent non-Anthropic implementation to compare against a Cla

• feature-executor

  Implements ONE feature workstream end-to-end to the team Definition of Done (Linear branch, scenario-matrix tests, 100% coverage, PR via the repo's PR skill, CodeRabbit-approved). Use for each workstream of a multi-PR feature build.

• implementer

  Cost-efficient implementer for work the session has already specified. Runs Sonnet by default; invoke with model="opus" for subtle or high-stakes tasks (concurrency, security-sensitive paths, hard debugging, wide refactors). Receives a complete spec — objective, files, interfaces, constraints, verif

• plan-requirements-reviewer
• production-hardening-reviewer
• security-controls-reviewer
• security-threat-modeling-reviewer

Similar plugins