~ / rigs / Maximumsoft-Co-LTD / claude-flightdeck

Maximumsoft-Co-LTD/claude-flightdeck

Portable AI-workflow control plane for Claude Code — one install.sh ships specialized agents, user-invocable skills, always-on rules, lint/audit/secret hooks, the 6-gate review, design templates + sprint discipline, an /onboard wizard, and

↗ GitHub ★ 2 MIT updated 4mo ago project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~3.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude ./rig-claude-flightdeck  # 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 Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/backlog-migrate .claude/skills/backlog-migrate
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/document .claude/skills/document
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/flightdeck-feedback .claude/skills/flightdeck-feedback
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/idea .claude/skills/idea
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/onboard .claude/skills/onboard
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/recover .claude/skills/recover
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/retro .claude/skills/retro
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/review .claude/skills/review
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/ship .claude/skills/ship
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/status .claude/skills/status
$ npx degit Maximumsoft-Co-LTD/claude-flightdeck/core/.claude/skills/work .claude/skills/work
$ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/backend-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/design-doc-writer.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/design-doc-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/frontend-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/onboarding-engineer.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/onboarding-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/orchestrator.md
$ curl -fsSL --create-dirs -o .claude/agents/senior-tech-lead.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/senior-tech-lead.md
$ curl -fsSL --create-dirs -o .claude/agents/sprint-retro-author.md https://raw.githubusercontent.com/Maximumsoft-Co-LTD/claude-flightdeck/main/core/.claude/agents/sprint-retro-author.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (11)

Subagents (7)

backend-engineer
model: sonnet
Implement a backend / service feature in {{PROJECT_NAME}} ({{TECH_STACK_DESC}}) — a handler/endpoint, a use-case or service, a data-access change, a migration, a job/worker, a message producer/consume
design-doc-writer
model: opus
Author zero-fix Design Docs that let a downstream implementation agent ship in one pass with no re-delegation. Target ≥500 lines for non-trivial tasks (correlates with zero post-delegation rework). In
frontend-engineer
model: sonnet
Implement a frontend / UI feature in {{PROJECT_NAME}} — a page/route, a component, a piece of client state, a form, an API client call, an i18n change. Architecture-agnostic: reads the project's OWN s
onboarding-engineer
model: opus
Author the **first** set of control-plane artifacts for a freshly-installed project — root CLAUDE.md, per-area CLAUDE.md, brain-hot.md A011+ drafts, codebase-orientation.md, team-conventions.md, and `
{{AGENT_PREFIX}}-orchestrator
model: opus
Top-level PM / orchestrator agent for {{PROJECT_NAME}}. Use to pick the next task, plan a sprint phase, sequence parallel work, or summarize current sprint state. Reads docs/project/sprints/S<N>/tasks
senior-tech-lead
model: sonnet
Comprehensive review of code quality, architecture compliance, cross-component contract sync, and requirement fulfillment across {{PROJECT_NAME}}. Use after a coding agent finishes a feature, before m
sprint-retro-author
model: sonnet
Author a sprint retro for {{PROJECT_NAME}} at sprint close. Reads sprint board (tasks.md) + collected mini-retros + lessons, produces docs/project/sprints/NN/retro.md. Knows the move-prose-on-close di

Similar rigs

copied ✓