Project Starter — Sistema de Contexto para Claude Code
FriedDev/project-starter
Estrutura de projeto com contexto em 3 camadas, hooks e skills para Claude Code
Ver no GitHubScaffold de projeto que fornece contexto estruturado e não-conflitante ao Claude Code em camadas (always-on, on-demand e path-scoped). Inclui hooks de enforcement, skills JSM para workflow da sessão, e funciona tanto para projetos web full-stack quanto CLI. Elimina drift de contexto entre sessões.
Instalação
npx convez-ai FriedDev/project-starter1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Configurar novo projeto web ou CLI com contexto persistente para Claude Code
- Padronizar regras de código, arquitetura e compliance por escopo de arquivo
- Implementar enforcement automático (typecheck, bloqueio de credentials)
- Manter coerência de contexto e workflow entre múltiplas sessões de desenvolvimento
Veredito

Ferramenta bem-pensada que resolve fragmentação de contexto em sessões longas com Claude Code. A arquitetura de 3 camadas é elegante, mas exige disciplina para manter `CLAUDE.md` enxuto e contextos organizados.
README
A tradução para o português deste README ainda está na fila.
project-starter
A Claude Code project scaffold that gives the agent complete, non-conflicting context from the first session — and keeps it from drifting across sessions. Works for full-stack web projects and CLI / no-UI projects alike.
It is built on three layers:
| Layer | File(s) | When it loads | Cost |
|---|---|---|---|
| Always-on brain | CLAUDE.md | Every message | Small (keep it < 200 lines) |
| On-demand specs | context/*.md | Read at session start | Loaded deliberately |
| Path-scoped rules | .claude/rules/*.md | Only when a matching file is open | Zero unless relevant |
Plus hooks for hard enforcement (typecheck on every TS edit, block credential leaks in shell
commands) and the JSM Agent Skills (/architect, /remember, /review, /recover,
/imprint) for the session workflow.
Start a new project
git clone https://github.com/FriedDev/project-starter.git my-new-project
cd my-new-project
bash setup.sh
setup.sh does four things:
- Installs the skills —
npx skills@latest add JavaScript-Mastery-Pro/skills(this is why the repo itself ships no skill files — see "How skills work" below). - Wires the symlinks — Claude Code discovers skills in
.claude/skills/, but the installer writes them to.agents/skills/. The script symlinks one to the other. - Makes the hooks executable —
chmod +x .claude/hooks/*.sh. - Resets git — deletes the starter's history and runs
git initso your project starts clean. Passbash setup.sh --keep-gitto skip this.
Requires Node.js (for
npx) and network access on first run. Ifnpxis missing, the script tells you exactly what to run later — everything else still completes.
After setup, fill in the context/ files and edit CLAUDE.md, then open Claude Code.
How skills work (read this if /architect is missing)
The skills are not committed to this repo. They are installed at setup time so you always get the latest version. This means:
- A fresh
git clonehas empty.agents/skills/and.claude/skills/. That is expected. - The skills only exist after you run
bash setup.sh. .agents/and.claude/skills/are gitignored, so they never get committed back.
If /architect, /remember, /review, /recover, or /imprint aren't available in Claude Code,
you haven't run setup.sh yet — or the npx step failed. Re-run:
npx skills@latest add JavaScript-Mastery-Pro/skills
bash setup.sh # re-wires symlinks idempotently
What's in the box
CLAUDE.md always-loaded brain — session bootstrap + non-negotiable rules
setup.sh one-time setup (run after clone)
README.md this file
.gitignore excludes memory, secrets, node_modules, and the installed skills
context/
project-overview.md what the project is and does (fill in)
architecture.md stack, folders, system boundaries, schema (fill in)
code-standards.md TypeScript + patterns (web section is deletable for CLI projects)
library-docs.md how each third-party library is used here (fill in)
build-plan.md phased feature list (fill in)
progress-tracker.md living status — read LAST every session (fill in as you go)
.claude/
settings.json permissions allowlist + hook wiring (portable, no hardcoded paths)
hooks/
typecheck-on-edit.sh runs `npm run typecheck` after any .ts/.tsx edit
block-credential-leak.sh blocks shell commands with inline secrets
rules/
core-code.md UNIVERSAL — fires for src/ cli/ commands/ lib/ agent/ (keep always)
agent-code.md agent/AI logic rules
components.md web only — React components
api-routes.md web only — app/api route handlers
server-actions.md web only — actions/
memory/
MEMORY.md auto-memory index (gitignored beyond this seed)
Web project vs CLI / no-UI project
The scaffold is the same; you delete what doesn't apply.
- Web (Next.js) project — keep everything as-is.
- CLI / no-UI project:
- Delete
.claude/rules/components.md,api-routes.md,server-actions.md. - Delete the
# Web (Next.js)section ofcontext/code-standards.md(it's fenced with clear start/end markers). - Keep
core-code.md— it coverssrc/,cli/,commands/,lib/with stack-neutral rules.
- Delete
The template note at the top of CLAUDE.md says the same thing, so the agent sees it too.
Session workflow
| When | Run |
|---|---|
| Start of session (continuing work) | /remember restore |
| Before any complex feature | /architect |
| After any feature | /review |
| Broken after one fix attempt | /recover |
| End of session | /remember save |
New session with no prior save: read CLAUDE.md, then all context/ files in order, ending with
progress-tracker.md.
Updating the starter itself
This repo is the source of truth for the pattern. To improve it: clone with --keep-git
(bash setup.sh --keep-git), make changes, and push back to project-starter. Don't commit
installed skills, memory.md, or secrets — .gitignore already blocks them.