~ / rigs / brayandiazc / project-starter-template-en-ai

brayandiazc/project-starter-template-en-ai

AI-ready template to start any project: professional documentation base + AGENTS.md/CLAUDE.md, example Claude Code subagents & skills, and a lightweight spec flow. English version.

↗ GitHub ★ 3 MIT updated 17d ago project Claude CodeCodex
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~3.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit brayandiazc/project-starter-template-en-ai/.claude ./rig-project-starter-template-en-ai  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/accessibility-audit .claude/skills/accessibility-audit
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/commit .claude/skills/commit
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/configure-repo .claude/skills/configure-repo
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/copywriting .claude/skills/copywriting
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/design-system-audit .claude/skills/design-system-audit
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/i18n-parity .claude/skills/i18n-parity
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/identity .claude/skills/identity
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/instantiate .claude/skills/instantiate
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/migration-guard .claude/skills/migration-guard
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/new-adr .claude/skills/new-adr
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/new-spec .claude/skills/new-spec
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/open-issue .claude/skills/open-issue
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/open-pr .claude/skills/open-pr
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/port-change .claude/skills/port-change
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/prototype .claude/skills/prototype
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/release .claude/skills/release
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/seo-audit .claude/skills/seo-audit
$ npx degit brayandiazc/project-starter-template-en-ai/.claude/skills/update-template .claude/skills/update-template
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/designer.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/designer.md
$ curl -fsSL --create-dirs -o .claude/agents/doc-keeper.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/doc-keeper.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-author.md https://raw.githubusercontent.com/brayandiazc/project-starter-template-en-ai/main/.claude/agents/test-author.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Read(**/.env)",
      "Read(**/.env.local)",
      "Read(**/.env.development)",
      "Read(**/.env.development.local)",
      "Read(**/.env.production)",
      "Read(**/.env.production.local)",
      "Read(**/.env.staging)",
      "Read(**/.env.test)",
      "Read(**/.env.test.local)",
      "Read(**/*.pem)",
      "Read(**/*.key)",
      "Read(**/id_rsa)",
      "Read(**/id_ed25519)",
      "Read(**/id_ecdsa)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/git-guardrails.sh"
          },
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/secret-guardrails.sh"
          }
        ]
      },
      {
        "matcher": "Write|Edit|NotebookEdit",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/secret-guardrails.sh"
          },
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/spec-guardrails.sh"
          }
        ]
      }
    ]
  }
}

Skills (18)

Subagents (6)

architect
model: inherit
Plans an implementation approach BEFORE any code is written. Use when starting a non-trivial feature, refactor, or integration to produce a design grounded in the project's existing architecture and d
debugger
model: inherit
Reproduces a reported failure, isolates its root cause, and proposes the minimal fix. Use when there is a failing test, error, or bug report to diagnose. Fixes only the cause; does not refactor beyond
designer
model: inherit
Product designer who builds and reviews the views — turns the screen map into views faithful to the design system in design/ (tokens, native primitives, motion, both themes, i18n) and reviews the visu
doc-keeper
model: inherit
Keeps documentation in sync after a code change. Use after a feature, refactor, or decision lands to update architecture docs, add or amend ADRs, and append to the changelog. Does not touch production
security-reviewer
model: inherit
Reviews a change set against the four areas SECURITY.md declares fail silently — authorization, input validation, sessions, and webhook signatures — plus secrets and injection. Use it before merging a
test-author
model: inherit
Writes and extends automated tests following the project's testing conventions, then runs the test suite. Use when new code lacks coverage or when adding tests for a bug fix or feature. Covers the hap

Hooks (4)

eventmatcherruns
PreToolUseBash$CLAUDE_PROJECT_DIR/.claude/hooks/git-guardrails.sh
PreToolUseBash$CLAUDE_PROJECT_DIR/.claude/hooks/secret-guardrails.sh
PreToolUseWrite|Edit|NotebookEdit$CLAUDE_PROJECT_DIR/.claude/hooks/secret-guardrails.sh
PreToolUseWrite|Edit|NotebookEdit$CLAUDE_PROJECT_DIR/.claude/hooks/spec-guardrails.sh

Permissions

deny (14)
Read(**/.env)
Read(**/.env.local)
Read(**/.env.development)
Read(**/.env.development.local)
Read(**/.env.production)
Read(**/.env.production.local)
Read(**/.env.staging)
Read(**/.env.test)
Read(**/.env.test.local)
Read(**/*.pem)
Read(**/*.key)
Read(**/id_rsa)
Read(**/id_ed25519)
Read(**/id_ecdsa)
ask (0)
—
allow (5)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(gh pr view:*)
Bash(gh pr list:*)

Similar rigs

copied ✓