VexiloGuides

Claude Code Guide

Best practices & tricks

Eight battle-tested moves that combine gstack + ECC + Auto Agent.

Best practices & tricks

Eight battle-tested moves built around three companion tools — gstack commands, ECC Skills, and Auto Agent. Each one is a concrete scenario, the right way to combine commands, and why that combination wins.

1

/using-superpowers is your master switch — what you lose without it

The very first message of every new conversation should be this one. Without it, ECC Skills won't auto-detect, and skills like /tdd-workflow, /systematic-debugging, or /verification-loop will only fire when you type them in by hand — twice the work for the same result. Once /using-superpowers has run, Claude reads keywords like "write tests", "fix this bug", or "run verification" and pulls in the matching skill automatically.

First message of every new conversation → /using-superpowers
2

Three reviews in parallel — one wait, one third the time

Each tool brings its own angle, so run them all at once instead of in sequence. In a single message, fire /review (gstack engineer scoring) + /security-review (ECC deep security) + code-reviewer (Auto quality check). They're independent, so the total wait equals the slowest one. Running them serially is just wasted minutes.

Fire /review · /security-review · code-reviewer in parallel
3

Manual vs. auto — don't double-spend tokens

Once Claude finishes writing code, Auto Agent has already run code-reviewer / security-reviewer / build-error-resolver for you. Don't type /review on top — that's tokens for no extra info. Save the manual deep commands for milestones (right before merging a PR): /cso (OWASP Top 10 + STRIDE threat modeling — Auto Agent does not run this for you) and /qa (real browser-click testing).

Day-to-day = Auto Agent · Milestones = manual deep commands (/cso · /qa · /benchmark)
4

The 6-question dialogue in /office-hours — how to ask for a good plan

/office-hours feeds /autoplan. Vague input → vague plan. Use this one-line frame: "I want to build [X] for [user Y] to solve [pain point Z]; the known constraints are [A, B]." Miss one of the three and you'll get questioned back.

❌ "Help me build a login"  ✅ "Build email + OAuth login for SaaS users to solve multi-device sync, constraints: ship in 7 days + Supabase only"
5

PROJECT_STATE.md + /retro — keep context across days

Before signing off, write your current progress into PROJECT_STATE.md (gstack ships a template). Next morning, the first message of the new conversation is that file plus /using-superpowers, and Claude is right back where you left off. After every milestone, run /retro and write the sticking points into RETRO.md — read it before starting the next feature so you don't trip on the same things twice.

Wrap up: PROJECT_STATE.md · Start: paste it + /using-superpowers · Milestone: /retro
6

Model tier + cost rhythm

Three default tiers: subagents (the auto-fired code-reviewer / security-reviewer / etc.) run on Haiku 4.5 — saves 70% on cost. Main conversation runs on Sonnet 4.6. Only switch to Opus for deep-reasoning moments like /cso or architect, then switch back. Inside /autoplan, the CEO / engineering / design viewpoints already pick the right model for each role — you don't need to manage that.

Daily Sonnet · Subagents Haiku · Opus only for /cso and major architectural decisions
7

Where in the 9-stage flow you should start a fresh conversation

Context windows have limits. The 9-stage flow has three natural break points: after stage 2 planning (PRD is on disk), after stage 4 development (code is committed), and after stage 6 review (report is filed). Before switching, make sure all the key state lives in files — the new conversation picks up via PROJECT_STATE.md plus your committed code. Claude auto-compacts when context hits 50%, but switching deliberately is cleaner.

After plan · after dev · after review → fresh conversation, state via files
8

/design-shotgun for 3–5 options — never pick from one

Jumping straight to /ui-ux-pro-max is a common mistake — you get one design with nothing to compare against, which isn't really a decision. Right order: /design-consultation (clarify product positioning) → /design-shotgun (diverge into 3–5 options at once) → pick a direction → /ui-ux-pro-max (curate palette and fonts from the 67-style library) → /design-html (HTML preview) → /frontend-design (production code).

Diverge first (shotgun), then converge (pro-max). Don't skip steps.
One-line summary: Three tools, three jobs — gstack gives you angles (CEO / engineering / design / QA / CSO), ECC gives you process (test first, search first, debug first), Auto Agent backstops quality. Day-to-day, let Auto run; for milestones, you run the deep commands. State lives in files; rotate conversations when they fill up.
Read next:
  • "Full project development flow" — the complete command chain across all 9 stages
  • "UI/UX Pro Max guide" — the deep-dive for tip #8
Open the full interactive index →

Vexilo is the missing index for Claude Code — 31 agents, 125 commands, 123 skills and more, organized by scenario. Browse free; unlock search, filters and one-click CLAUDE.md export with a one-time $19 licence.