agentrigs
+ submit rig
~ / rigs / julian-najas / manual-claude-code

julian-najas/manual-claude-code

Guia Definitiva de Claude Code en espanol + manual profesional. Verificado contra CLI 2.1.228.

↗ GitHub ★ 0 NOASSERTION updated today project Claude Code Claude plugin
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~3.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit julian-najas/manual-claude-code/D2-verificador/sonda-esquema/.claude ./rig-manual-claude-code  # 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 julian-najas/manual-claude-code/D6-repo-feo/gestor-pedidos/.claude/skills/auditar-endpoint .claude/skills/auditar-endpoint
$ npx degit julian-najas/manual-claude-code/entregables/plantillas/skills/poner-al-dia .claude/skills/poner-al-dia
$ npx degit julian-najas/manual-claude-code/entregables/plantillas/skills/postmortem .claude/skills/postmortem
$ npx degit julian-najas/manual-claude-code/entregables/plantillas/skills/preparar-release .claude/skills/preparar-release
$ npx degit julian-najas/manual-claude-code/entregables/plantillas/skills/revisar-cambio .claude/skills/revisar-cambio

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(./secretos/**)",
      "Edit(./secretos/**)",
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./datos/*.db)",
      "Bash(curl *)",
      "Bash(wget *)"
    ],
    "ask": [
      "Bash(git push *)",
      "Bash(python app.py)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Read|Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/hooks/veto-secretos.sh"
          }
        ]
      },
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/hooks/veto-credenciales.sh"
          }
        ]
      }
    ]
  },
  "sandbox": {
    "enabled": true
  }
}

MCP servers (1)

serversourceest. tokens
pedidos local / custom 2.5k

Skills (5)

auditar-endpointponer-al-diapostmortempreparar-releaserevisar-cambio

Hooks (3)

eventmatcherruns
PreToolUseRead|Edit|Write${CLAUDE_PROJECT_DIR}/hooks/veto-secretos.sh
PreToolUseWrite|Edit${CLAUDE_PROJECT_DIR}/hooks/veto-credenciales.sh
PostToolUseEdit|Write${CLAUDE_PROJECT_DIR}/hooks/formatear.sh

Permissions

deny (7)
Read(./secretos/**)
Edit(./secretos/**)
Read(./.env)
Read(./.env.*)
Read(./datos/*.db)
Bash(curl *)
Bash(wget *)
ask (2)
Bash(git push *)
Bash(python app.py)
allow (3)
Bash(git status)
Bash(git diff *)
Bash(python3 -m pytest *)

Similar rigs

ArtVsMark/Engineering-Incidents-Playbook
Правила работы с Claude Code и конвейером GitHub — каждое с историей поломки, из которой выросло · Incident-based rules for Claude Code and GitHub: every rule grew out of a real failure, with the incident, the mechanism behind it, and where
★ 5 project Claude CodeCodex 7 skills 2 hooks 7d ago
Pragmatist 7.9k tok ·
MakiDevelop/claude-skills
Reusable skill packs for Claude Code CLI — 14 ready-to-use skills for data analysis, image generation, career tools, and more.
★ 3 collection Claude Code 16 skills 28d ago
Skill Collector 598 tok ·
boshu2/agentops
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.
★ 447 project Claude CodeCodex 28 skills 4 agents 5d ago
Skill Collector 5.7k tok ·
SethGammon/Citadel
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
★ 924 project Claude CodeCodex 5 mcp 48 skills 7 agents 13d ago
Orchestrator 38.0k tok ·
copied ✓