cdeust/ai-architect-mcp-spec
Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host suppor
field: AI / ML workflow: PR / code reviewSecurity reviewTesting & TDDPlanning & specsDocs runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~3.5k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit cdeust/ai-architect-mcp-spec/.claude ./rig-ai-architect-mcp-spec # 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 cdeust/ai-architect-mcp-spec/skills/audit-prd .claude/skills/audit-prd $ npx degit cdeust/ai-architect-mcp-spec/skills/validate-spec .claude/skills/validate-spec
$ curl -fsSL --create-dirs -o .claude/agents/code-quality-reviewer.md https://raw.githubusercontent.com/cdeust/ai-architect-mcp-spec/main/.claude/agents/code-quality-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-accuracy-reviewer.md https://raw.githubusercontent.com/cdeust/ai-architect-mcp-spec/main/.claude/agents/documentation-accuracy-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/cdeust/ai-architect-mcp-spec/main/.claude/agents/performance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-code-reviewer.md https://raw.githubusercontent.com/cdeust/ai-architect-mcp-spec/main/.claude/agents/security-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-coverage-reviewer.md https://raw.githubusercontent.com/cdeust/ai-architect-mcp-spec/main/.claude/agents/test-coverage-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| prd-gen env: PRD_GEN_SKILL_CONFIG | local / custom | 2.5k |
Skills (2)
Subagents (5)
| code-quality-reviewer model: inherit | Use this agent when you need to review code for quality, maintainability, and adherence to best practices. Examples:\n\n- After implementing a new feature or function:\n user: 'I've just written a fu |
| documentation-accuracy-reviewer model: inherit | Use this agent when you need to verify that code documentation is accurate, complete, and up-to-date. Specifically use this agent after: implementing new features that require documentation updates, m |
| performance-reviewer model: inherit | Use this agent when you need to analyze code for performance issues, bottlenecks, and resource efficiency. Examples: After implementing database queries or API calls, when optimizing existing features |
| security-code-reviewer model: inherit | Use this agent when you need to review code for security vulnerabilities, input validation issues, or authentication/authorization flaws. Examples: After implementing authentication logic, when adding |
| test-coverage-reviewer model: inherit | Use this agent when you need to review testing implementation and coverage. Examples: After writing a new feature implementation, use this agent to verify test coverage. When refactoring code, use thi |
Slash commands (2)
/review-pr/generate-prd
Similar rigs
anthropics/claude-code-action
—
Orchestrator 2.3k tok · · Q18
cdeust/cortex-viz
Cross-platform visualization MCP for Cortex — host-neutral live activity from Codex, Gemini CLI, Claude Code, and other MCP clients; memory galaxy, execution trace, knowledge graph, consolidation board, and wiki. Read-only, browser-based, w
Orchestrator 821 tok · · Q0
cdeust/session-optimizer
Cross-platform prompt refinement for Codex, Gemini CLI, and Claude Code, plus Claude-native context guard and telemetry statusline plugins. Portable refine-gate binds vague prompts to evidence; optional hooks enforce checkpoints, track suba
Orchestrator 681 tok · · Q0
matiaspautasso/specdriven-ai-kit
The missing workflow layer for AI-assisted software development. SDD + BDD + TDD enforced via agents, commands, and templates. Works with Claude Code, Cursor, Windsurf, and Codex.
Orchestrator 2.3k tok · · Q3