A pipeline of specialist agents for Claude Code that takes work from spec to deployment. An independent model checks each stage before the next one builds on it, and spending caps stop work instead of only warning. The user keeps the final say on what is built, how, and whether it ships.
@avelikiygreat_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided…
@avelikiyCatalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or…
@avelikiyAnalyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component…
@avelikiyShared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the…
@avelikiyAfter a build is delivered, delete its intermediate copies and old versions — keep exactly the version that runs and one previous…
@avelikiyStructured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a…
@avelikiyMake a slow CI pipeline or build faster by measuring it first — per-step durations, the slowest step, a target — then one change…
@avelikiyRun the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact…
@avelikiyHow to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick,…
@avelikiyStandardized cost-estimation framework for great_cto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the…
@avelikiyDistils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable…
@avelikiySpawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and…
@avelikiyBookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes.…
@avelikiyUS adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off…
@avelikiyBuilds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-*.md files (golden…
@avelikiyDesigns and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md…
@avelikiyAI-specific pre-implementation threat modelling for ai-system / agent-product archetypes. Outputs threat model TM-{slug}.md and…
@avelikiyAPI platform / dev-API pre-implementation reviewer. Outputs threat model TM-{slug}.md.
@avelikiyProject-scaffolding builder that stands up a working base application from the pinned stack-baseline so senior-dev implements…
@avelikiyUse when starting any new feature. Creates architecture docs, ADRs, cost estimates, Well-Architected review. Always first in the…
@avelikiyAuthentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js…
@avelikiyUse when CI or a build is red. Names each red check's cause (false test, broken gate, real regression, flaky), lands a minimal…
@avelikiyCLI tool pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off CLI surface decisions before senior-dev…
@avelikiyUS defense-contractor (GovCon) pre-implementation reviewer. Outputs threat model TM-cmmc-{slug}.md and signs off the…
@avelikiyManage an agent like an employee — review its record, generate its evals, evolve its prompt against held-out evals, or retire it.
@avelikiyHave an existing codebase? Run it — you get the detected stack, a gap list with severity and file:line evidence, a task per gap,…
@avelikiyOpen the great_cto admin board at http://localhost:3141 (Kanban, cost, pipeline, inbox, memory). Starts it in background if not…
@avelikiyAfter a session or an incident, turn what happened into reusable knowledge — `learn` captures this session's lessons,…
@avelikiyFriday review — what shipped, what broke, what it cost; add `cost`, `slo`, `gov` or `sessions` for the detail. Weekly engineering…
@avelikiySomething off with great_cto, or just upgraded it? Run it — you get a health report (pipeline state, missing artefacts, hooks,…
@avelikiySigned gate-exception registry — replace ad-hoc --admin / --no-verify bypasses with an auditable, signed, expiring record (who ·…
@avelikiyForgot a command, or new to great_cto? Run it — you get the command card: the five everyday commands, the rest by when you need…
@avelikiySomething waiting on you? Run it — you get only the decisions that need you: open gates, blockers, P0s and pending approvals,…
@avelikiyWhen you need to know who owns a path and who answers for it — the service ownership matrix (team, lead, on-call, SLA)…
@avelikiyBefore building on an unproven idea, get a timeboxed yes/no answer — start a hypothesis-driven POC that skips 80% of the…
@avelikiyWhen you half-remember something, find what this project already knows — session history and the documents written about it by…
@avelikiyIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
