jblossey/houserules
A CLI that makes your AI coding agents adhere to your rules, audits each change, and proves your intent is obeyed.
field: Developer tools workflow: Planning & specsPR / code reviewGit & commitsFrontend & designSecurity review
stack: Rust
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit jblossey/houserules/.claude ./rig-houserules # 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 jblossey/houserules/.claude/skills/designing .claude/skills/designing $ npx degit jblossey/houserules/.claude/skills/finishing-a-feature .claude/skills/finishing-a-feature $ npx degit jblossey/houserules/.claude/skills/houserules-step .claude/skills/houserules-step $ npx degit jblossey/houserules/.claude/skills/migrating-knowledge .claude/skills/migrating-knowledge $ npx degit jblossey/houserules/.claude/skills/orchestrating .claude/skills/orchestrating $ npx degit jblossey/houserules/.claude/skills/planning .claude/skills/planning $ npx degit jblossey/houserules/.claude/skills/project-knowledge .claude/skills/project-knowledge $ npx degit jblossey/houserules/.claude/skills/readme-rework .claude/skills/readme-rework
$ curl -fsSL --create-dirs -o .claude/agents/branch-reviewer.md https://raw.githubusercontent.com/jblossey/houserules/main/.claude/agents/branch-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/jblossey/houserules/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/jblossey/houserules/main/.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/task-reviewer.md https://raw.githubusercontent.com/jblossey/houserules/main/.claude/agents/task-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/branch-reviewer.md https://raw.githubusercontent.<redacted>.claude/agents/branch-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.<redacted>.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.<redacted>.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/task-reviewer.md https://raw.githubusercontent.<redacted>.claude/agents/task-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 *)"
]
}
} Skills (8)
designingfinishing-a-featurehouserules-stepmigrating-knowledgeorchestratingplanningproject-knowledgereadme-rework
Subagents (8)
| branch-reviewer | Reviews a whole branch before merge and proposes knowledge-base improvements from the batch's audits and reviews. Use for the final whole-branch review of every batch. |
| implementer | Implements one task from a task brief under this repository's rules. Use for every implementer dispatch in this repository. |
| spec-reviewer | Attacks a spec's decisions before the human sees it, reruns its probes, and files a spec-review. Use for every design review of a standard-tier batch. |
| task-reviewer | Reviews one task's diff for spec compliance, code quality, and rule adherence. Use for every task review and scoped re-review in this repository. |
| branch-reviewer | Reviews a whole branch before merge and proposes knowledge-base improvements from the batch's audits and reviews. Use for the final whole-branch review of every batch. |
| implementer | Implements one task from a task brief under this repository's rules. Use for every implementer dispatch in this repository. |
| spec-reviewer | Attacks a spec's decisions before the human sees it, reruns its probes, and files a spec-review. Use for every design review of a standard-tier batch. |
| task-reviewer | Reviews one task's diff for spec compliance, code quality, and rule adherence. Use for every task review and scoped re-review in this repository. |
Hooks (3)
| event | matcher | runs |
|---|---|---|
| SessionStart | compact | ${CLAUDE_PROJECT_DIR}/tools/claude-session-start.sh compact |
| SessionStart | * | ${CLAUDE_PROJECT_DIR}/tools/reference-session-start.sh |
| SessionStart | compact | ${CLAUDE_PROJECT_DIR}/tools/claude-session-start.sh compact |
Similar rigs
raalarcon9705/gated-dev-agents
Claude Code plugin: evidence-gated implementer, spec/code-quality reviewers, blind pre-mortem, QA verifier and e2e runner subagents + gate skills
Orchestrator 687 tok · · Q0
Tamircohen28/tamirs-superpowers
A portable agent toolkit — 31 skills, 10 specialist agents, worktree hooks and MCP stubs — shipped from one canonical source to six agent surfaces across five platforms: Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI and OpenCode.
Orchestrator 7.0k tok · · Q18
shoklah/claude-workflow-template
An agentic workflow template for Claude Code: hooks, custom agents and a CLAUDE.md section
Orchestrator 3.8k tok · · Q0
shoklah/roland
An agentic workflow template for Claude Code: hooks, custom agents and a CLAUDE.md section
Orchestrator 3.9k tok · · Q0