jlema0590/aikya-harness
AI engineering harness for Claude Code with guided project setup, specialized agents, reusable skills, automated quality gates, and living documentation.
field: Cloud & infrastructure workflow: PR / code reviewPlanning & specsFrontend & designTesting & TDDSecurity review
stack: Python
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Quality 51/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit jlema0590/aikya-harness/.claude ./rig-aikya-harness # 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 jlema0590/aikya-<redacted>-engineering .claude/skills/angular-engineering $ npx degit jlema0590/aikya-<redacted>-automation .claude/skills/ansible-automation $ npx degit jlema0590/aikya-<redacted>-performance .claude/skills/astro-performance $ npx degit jlema0590/aikya-<redacted>-pipelines .claude/skills/cicd-pipelines $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/clean-architecture $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/cloud-architecture $ npx degit jlema0590/aikya-<redacted>-security .claude/skills/cloud-security $ npx degit jlema0590/aikya-<redacted>-review .claude/skills/code-review $ npx degit jlema0590/aikya-<redacted>-best-practices .claude/skills/docker-best-practices $ npx degit jlema0590/aikya-<redacted>-engineering .claude/skills/dotnet-engineering $ npx degit jlema0590/aikya-<redacted>-driven-architecture .claude/skills/event-driven-architecture $ npx degit jlema0590/aikya-<redacted>-optimization .claude/skills/finops-optimization $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/flutter-architecture $ npx degit jlema0590/aikya-<redacted>-deployment .claude/skills/helm-deployment $ npx degit jlema0590/aikya-<redacted>-engineering .claude/skills/java-engineering $ npx degit jlema0590/aikya-<redacted>-engineering .claude/skills/kotlin-engineering $ npx degit jlema0590/aikya-<redacted>-operations .claude/skills/kubernetes-operations $ npx degit jlema0590/aikya-<redacted>-deployment .claude/skills/kustomize-deployment $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/layered-architecture $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/microservices-architecture $ npx degit jlema0590/aikya-<redacted>-monolith-architecture .claude/skills/modular-monolith-architecture $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/nextjs-architecture $ npx degit jlema0590/aikya-<redacted>-api-design .claude/skills/node-api-design $ npx degit jlema0590/aikya-<redacted>-engineering .claude/skills/python-engineering $ npx degit jlema0590/aikya-<redacted>-engineering .claude/skills/react-engineering $ npx degit jlema0590/aikya-<redacted>-audit .claude/skills/security-audit $ npx degit jlema0590/aikya-<redacted>-iac .claude/skills/terraform-iac $ npx degit jlema0590/aikya-<redacted>-strategy .claude/skills/testing-strategy $ npx degit jlema0590/aikya-<redacted>-architecture .claude/skills/vue-architecture $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/architecture-review .claude/skills/architecture-review $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/bugfix .claude/skills/bugfix $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/documentation-sync .claude/skills/documentation-sync $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/feature .claude/skills/feature $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/mobile-feature .claude/skills/mobile-feature $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/project-bootstrap .claude/skills/project-bootstrap $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/project-init .claude/skills/project-init $ npx degit jlema0590/aikya-harness/src/aikya/resources/project_template/.claude/skills/verify .claude/skills/verify
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-maintainer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/documentation-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-engineer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/mobile-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-reviewer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/qa-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/jlema0590/aikya-harness/main/src/aikya/resources/project_template/.claude/agents/security-reviewer.md
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(./.env)",
"Read(./.env.*)",
"Read(./**/.env)",
"Read(./**/.env.*)"
],
"ask": [
"Bash(git push *)",
"Bash(terraform apply *)",
"Bash(kubectl apply *)",
"Bash(docker push *)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PROJECT_DIR}/.claude/hooks/guard_bash.py\""
}
]
},
{
"matcher": "Skill",
"hooks": [
{
"type": "command",
"command": "python3 -B \"${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py\""
}
]
}
]
}
} Skills (37)
angular-engineeringansible-automationastro-performancecicd-pipelinesclean-architecturecloud-architecturecloud-securitycode-reviewdocker-best-practicesdotnet-engineeringevent-driven-architecturefinops-optimizationflutter-architecturehelm-deploymentjava-engineeringkotlin-engineeringkubernetes-operationskustomize-deploymentlayered-architecturemicroservices-architecturemodular-monolith-architecturenextjs-architecturenode-api-designpython-engineeringreact-engineeringsecurity-auditterraform-iactesting-strategyvue-architecturearchitecture-reviewbugfixdocumentation-syncfeaturemobile-featureproject-bootstrapproject-initverify
Subagents (8)
| architect model: inherit | Review software architecture, interfaces and risk before complex changes using read-only repository evidence. |
| backend-engineer model: inherit | Implement approved backend endpoints, business services, persistence and interfaces using the verified project stack. |
| developer model: inherit | Apply small approved code changes and regression tests while respecting actual repository conventions. |
| documentation-maintainer model: inherit | Review documentation impact, affected living pages and evidence without modifying user content by default. |
| frontend-engineer model: inherit | Implement approved React or Vue interfaces using the existing framework, accessibility rules and tests. |
| mobile-engineer model: inherit | Implement approved Android, iOS, Flutter or React Native features with platform-specific validation. |
| qa-reviewer model: inherit | Perform an independent, read-only QA review of acceptance criteria, regression coverage and observed results. |
| security-reviewer model: inherit | Inspect authentication, authorization, secrets and infrastructure security using read-only source evidence. |
Hooks (14)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|resume|fork | python3 "${CLAUDE_PROJECT_DIR}/src/aikya/resources/project_template/.claude/hooks/welcome.py" |
| PreToolUse | Bash | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/guard_bash.py" |
| PreToolUse | Skill | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| PostToolUse | Edit|Write | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/check_edit.py" |
| UserPromptSubmit | * | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/request_docs.py" |
| UserPromptSubmit | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| Stop | * | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/stop_docs.py" |
| SessionStart | startup|resume|fork | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/welcome.py" |
| SessionStart | * | python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/skills_ready.py" |
| PostToolUseFailure | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| SubagentStart | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| SubagentStop | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| StopFailure | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
| SessionEnd | * | python3 -B "${CLAUDE_PROJECT_DIR}/.claude/hooks/execution_status.py" |
Permissions
deny (4)
Read(./.env)
Read(./.env.*)
Read(./**/.env)
Read(./**/.env.*)
ask (4)
Bash(git push *)
Bash(terraform apply *)
Bash(kubectl apply *)
Bash(docker push *)
allow (0)
—
Similar rigs
theishandubey/claude-config
A complete Claude Code setup. An agent roster, an orchestration playbook, safe defaults and curated skills, installed with one command.
Orchestrator 5.0k tok · · Q5
minanyang/10x-agent
A multi-agent workflow for shipping code: agents plan, build and review, and nothing lands without evidence a script can check.
Orchestrator 1.3k tok · · Q0
HartBrook/staghorn
Sync Claude Code configs and skills from GitHub — for teams, communities, or across your personal projects. Run evals to verify your guidelines actually work.
Minimalist 196 tok · · Q18
juanagu/claude-code-config
Personal Claude Code global config: CLAUDE.md, subagents, and custom skills
Orchestrator 10.1k tok · · Q5