Hainrixz/the-architect
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every bui
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit Hainrixz/the-architect/agents ./rig-the-architect/agents $ npx degit Hainrixz/the-architect/commands ./rig-the-architect/commands $ npx degit Hainrixz/the-architect/skills ./rig-the-architect/skills
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 Hainrixz/the-architect/skills/architect .claude/skills/architect $ curl -fsSL --create-dirs -o .claude/agents/blueprint-validator.md https://raw.githubusercontent.com/Hainrixz/the-architect/main/agents/blueprint-validator.md $ curl -fsSL --create-dirs -o .claude/agents/blueprint-writer.md https://raw.githubusercontent.com/Hainrixz/the-architect/main/agents/blueprint-writer.md $ curl -fsSL --create-dirs -o .claude/agents/stack-researcher.md https://raw.githubusercontent.com/Hainrixz/the-architect/main/agents/stack-researcher.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 (1)
Subagents (3)
| blueprint-validator model: sonnet | Adversarially audits a finished blueprint bundle and returns PASS or FAIL with line-referenced findings. Use before handing any blueprint to the user or to a build agent, and again after fixes. Read-o |
| blueprint-writer model: opus | Composes the finished blueprint from the interview findings, the chosen shape, the runtime track, and the selected capabilities — and in bundle mode writes the whole bundle: blueprint.md, tasks.json, |
| stack-researcher model: sonnet | Resolves package versions and package identifiers against authoritative sources — the published artifact first, then the registry — before either is written into a blueprint. Use PROACTIVELY whenever |
Slash commands (6)
/architect-audit/architect-brownfield/architect-next/architect-quick/architect-refresh/architect
Similar rigs
novibe-org/novibe
Spec-driven development for coding agents — you manage the intent, the machine writes the code. Skills, conventions and git-hook guard rails.
Pragmatist 405 tok ·
peterzat/zat.env
Verification-first agentic coding harness for Claude Code.
Pragmatist 6.9k tok ·
KJ-devs/setupClaudeCode
—
Fort Knox 2.2k tok ·
BytesFromToby/plumbline
A "trust, but verify" workflow of AI-agent skills: prompt to verified code, every step trackable and deviations logged — plus an autonomous maintenance loop to keep a built project honest.
Pragmatist 1.7k tok ·