ajyadav013/claude-kit
The autonomous SDLC for Claude Code that won't pass a gate on an unproven verdict.
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 ajyadav013/claude-kit/agents ./rig-claude-kit/agents $ npx degit ajyadav013/claude-kit/commands ./rig-claude-kit/commands $ npx degit ajyadav013/claude-kit/skills ./rig-claude-kit/skills $ npx degit ajyadav013/claude-kit/hooks ./rig-claude-kit/hooks
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 ajyadav013/claude-kit/providers/codex/claude-kit/skills/accessibility-review .claude/skills/accessibility-review $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/alembic-migrations .claude/skills/alembic-migrations $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/anthropic-vertex-integration .claude/skills/anthropic-vertex-integration $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/api-and-interface-design .claude/skills/api-and-interface-design $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/api-integration .claude/skills/api-integration $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/api-pagination-filtering-sorting .claude/skills/api-pagination-filtering-sorting $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/archive-sprint .claude/skills/archive-sprint $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/async-python-patterns .claude/skills/async-python-patterns $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/auth-and-rbac .claude/skills/auth-and-rbac $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/backend-repo-architecture .claude/skills/backend-repo-architecture $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/backlog .claude/skills/backlog $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/browser-testing-with-devtools .claude/skills/browser-testing-with-devtools $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/bug-hunt .claude/skills/bug-hunt $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/ci-cd-and-automation .claude/skills/ci-cd-and-automation $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/ckit-command-abort .claude/skills/ckit-command-abort $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/ckit-command-init .claude/skills/ckit-command-init $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/ckit-command-sdlc .claude/skills/ckit-command-sdlc $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/ckit-command-status .claude/skills/ckit-command-status $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/code-review-and-quality .claude/skills/code-review-and-quality $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/code-simplification .claude/skills/code-simplification $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/component-design .claude/skills/component-design $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/configargparse-yaml-env-layering .claude/skills/configargparse-yaml-env-layering $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/consolidate-learnings .claude/skills/consolidate-learnings $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/containerization-and-deployment .claude/skills/containerization-and-deployment $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/context-engineering .claude/skills/context-engineering $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/cron-and-scheduled-jobs .claude/skills/cron-and-scheduled-jobs $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/data-engineering-bigquery-gcs .claude/skills/data-engineering-bigquery-gcs $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/debugging-and-error-recovery .claude/skills/debugging-and-error-recovery $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/decision .claude/skills/decision $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/dependency-verification .claude/skills/dependency-verification $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/deploy .claude/skills/deploy $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/deprecation-and-migration .claude/skills/deprecation-and-migration $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/design-patterns-and-conventions .claude/skills/design-patterns-and-conventions $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/design-system-ops .claude/skills/design-system-ops $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/distributed-systems-patterns .claude/skills/distributed-systems-patterns $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/django-async-patterns .claude/skills/django-async-patterns $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/django-migrations .claude/skills/django-migrations $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/django-react-integration .claude/skills/django-react-integration $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/django-rest-framework-packages .claude/skills/django-rest-framework-packages $ npx degit ajyadav013/claude-kit/providers/codex/claude-kit/skills/django-rest-framework-patterns .claude/skills/django-rest-framework-patterns
$ curl -fsSL --create-dirs -o .claude/agents/acceptance-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/acceptance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/auditor.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/auditor.md $ curl -fsSL --create-dirs -o .claude/agents/dependency-scanner.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/dependency-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/devils-advocate.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/devils-advocate.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-tester.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/e2e-tester.md $ curl -fsSL --create-dirs -o .claude/agents/em-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/em-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/incident-responder.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/incident-responder.md $ curl -fsSL --create-dirs -o .claude/agents/maker-checker-maker.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/maker-checker-maker.md $ curl -fsSL --create-dirs -o .claude/agents/maker-checker-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/maker-checker-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/merge-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/merge-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/observability-engineer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/observability-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/owasp-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/owasp-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/pentest-scanner.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/pentest-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/policy-validator.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/policy-validator.md $ curl -fsSL --create-dirs -o .claude/agents/pr-raiser.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/pr-raiser.md $ curl -fsSL --create-dirs -o .claude/agents/risk-classifier.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/risk-classifier.md $ curl -fsSL --create-dirs -o .claude/agents/sdlc-code-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/sdlc-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/secret-scanner.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/secret-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-backend-dev.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/senior-backend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/senior-backend-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/senior-backend-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-frontend-dev.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/senior-frontend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/senior-frontend-reviewer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/senior-frontend-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-tester.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/senior-tester.md $ curl -fsSL --create-dirs -o .claude/agents/spec-doc-writer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/spec-doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/story-planner.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/story-planner.md $ curl -fsSL --create-dirs -o .claude/agents/technical-architect.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/technical-architect.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/tester.md $ curl -fsSL --create-dirs -o .claude/agents/ui-designer.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/ui-designer.md $ curl -fsSL --create-dirs -o .claude/agents/unit-tester.md https://raw.githubusercontent.com/ajyadav013/claude-kit/main/agents/unit-tester.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 (127)
accessibility-reviewalembic-migrationsanthropic-vertex-integrationapi-and-interface-designapi-integrationapi-pagination-filtering-sortingarchive-sprintasync-python-patternsauth-and-rbacbackend-repo-architecturebacklogbrowser-testing-with-devtoolsbug-huntci-cd-and-automationckit-command-abortckit-command-initckit-command-sdlcckit-command-statuscode-review-and-qualitycode-simplificationcomponent-designconfigargparse-yaml-env-layeringconsolidate-learningscontainerization-and-deploymentcontext-engineeringcron-and-scheduled-jobsdata-engineering-bigquery-gcsdebugging-and-error-recoverydecisiondependency-verificationdeploydeprecation-and-migrationdesign-patterns-and-conventionsdesign-system-opsdistributed-systems-patternsdjango-async-patternsdjango-migrationsdjango-react-integrationdjango-rest-framework-packagesdjango-rest-framework-patternsdjango-service-patternsdoc-consolidationdocker-composedocker-shareddockerfile-backenddockerfile-frontenddocumentation-and-adrsdoubt-driven-developmentedge-to-service-trust-boundaryexecuteexpressfastapi-service-patternsfile-export-and-reportingfrontend-repo-architecturefrontend-ui-engineeringgcp-cloud-run-github-actionsgcs-file-storage-patternsgit-workflow-and-versioninggrafana-dashboards-and-alertsgraphql-patternsidea-refineincident-postmortemincremental-implementationinterview-mekafka-config-drivenkubectl-operationskubernetes-workload-hardeninglangfuse-llm-tracinglibrary-reviewllm-caching-strategiesllm-gateway-and-routingllm-inference-optimizationload-testingmaker-checkermanual-testmodernization-and-migrationmulti-tenancy-patternsnode-express-servicenode-objection-knexnotifications-and-messagingobject-oriented-designobservability-and-loggingotel-tracingover-engineering-reviewpentesterflow-pentestperformance-optimizationplanning-and-task-breakdownplaywright-verificationpydantic-schema-patternspython-dao-and-databaseradix-tailwind-component-patternsrag-and-model-tuningreact-hook-form-zod-patternsredis-caching-patternsrefresh-docsremembersafety-critical-patternsscopesdlcsecurity-and-hardeningsecurity-verificationshannon-ai-pentestshell-reviewshipping-and-launchsimplification-debtsmoke-testsource-driven-developmentspec-driven-developmentsprintstrix-ai-pentestsystem-design-patternstanstack-react-query-patternstask-tracker-synctemporal-config-driventemporal-developertest-driven-developmenttest-plan-reviewtesting-conventionsthreat-modelticketing-and-traceabilitytriageui-ux-designunit-testusing-agent-skillsvitest-rtl-msw-patternszap-vapt-scanningzustand-state-patterns
Subagents (33)
| acceptance-reviewer model: sonnet | Checks delivered work against every acceptance criterion in the spec, end to end, and confirms all prior gates actually passed. Use when work claims to be done and needs independent sign-off. Read-onl |
| auditor model: sonnet | Uses Chrome DevTools MCP to audit pages for accessibility, performance, responsive layout, and console errors. Read-only — produces audit reports. |
| dependency-scanner model: sonnet | Security sub-scanner agent. Audits project dependencies (backend and frontend) for known CVEs — direct and transitive — flags deprecated/outdated packages, and recommends pinned upgrades. Reports only |
| developer model: opus | Writes production code from approved specs. Works in an isolated git worktree and responds to code review feedback. Handles backend, frontend, or full-stack implementation depending on the project. |
| devils-advocate model: opus | Anti-sycophancy adversarial reviewer. Critiques a plan/spec before approval, and when a gate reaches unanimous PASS. Returns findings, a premortem, and a merits-and-costs balance sheet. Gates the pipe |
| devops-engineer model: sonnet | Delivery & operability agent. Owns the CI pipeline, build & packaging, release/rollback, environment & secrets, database migrations, and local dev experience for any stack. Container-optional. |
| e2e-tester model: sonnet | Writes end-to-end integration tests simulating real user interactions and validating full user journeys across the application. |
| em-reviewer model: sonnet | Engineering Manager planning adjudicator. De-duplicates one blind specialist panel, applies explicit decision rights, and issues the sole planning PASS or consolidated FAIL before code is written. |
| incident-responder model: sonnet | Production incident commander. Use when prod is broken — errors spiking, latency breach, dependency down, bad deploy. Triages severity, gathers signals, drives mitigation (rollback/flag) FIRST, then r |
| maker-checker-maker model: opus | Produces code, design, or specification artifacts for the managed maker-checker loop through a constrained output channel. It cannot mutate the workspace, run commands, delegate, or cause external eff |
| maker-checker-reviewer model: sonnet | Independently reviews the current code, design, or specification artifact against its frozen contract and returns an evidence-backed verdict. It is read-only, nondelegating, and cannot cause external |
| merge-reviewer model: sonnet | Verifies that parallel work streams (e.g., backend + frontend, or any independent development lanes) are consistent, compatible, and integration-ready. Gates pipeline progression at join points. |
| observability-engineer model: sonnet | Makes a service observable in production — SLOs and SLIs, health and readiness checks, structured logging, alert rules, request tracing. Use when a change needs monitoring or operational readiness. Ow |
| orchestrator model: opus | SDLC Pipeline Controller. Never writes code — only delegates, coordinates, and gates agent progression. Supports parallel execution lanes for independent work streams. |
| owasp-reviewer model: opus | Security sub-scanner. Reviews the change against the OWASP Top 10 (2021), tuned to the project's stack — access control (A01), injection (A03), authentication (A07), logging (A09). Reports findings wi |
| pentest-scanner model: sonnet | Dynamic security sub-scanner — runs a penetration test with an authorized installed tool (Strix, Shannon, PentesterFlow, or ZAP) and validates findings with real PoCs. Only for systems you are authori |
| policy-validator model: sonnet | Security sub-scanner. Validates required security policies — CORS allowlist, auth-endpoint rate limiting, secure session cookies, security headers, input validation, authz chain. PASS/FAIL. Reports on |
| pr-raiser model: sonnet | Final pipeline agent that runs lint, build, and tests, then creates a structured pull request with proper commit formatting. |
| risk-classifier model: sonnet | Classifies a task or change as low / medium / high / restricted risk and states the required protocol. Read-only — gates how much caution, review, and human approval the work needs before it proceeds. |
| sdlc-code-reviewer model: sonnet | Reviews code changes for bugs, security, performance, and spec compliance. Gates the pipeline — testing cannot start without reviewer approval. |
| secret-scanner model: sonnet | Security sub-scanner. Detects hardcoded secrets, API keys, tokens, passwords, connection strings, and private keys in code, config, compose, CI, and tests — plus accidental .env commits and secrets in |
| security-reviewer model: sonnet | Reviews a change for security problems — hardcoded secrets, vulnerable dependencies, OWASP Top 10 issues, missing security policies — via four parallel sub-scanners. Use when a change needs a security |
| senior-backend-dev model: sonnet | Senior backend developer agent. Handles API endpoint design, database work, migrations, authentication, authorization, and backend testing for any stack. |
| senior-backend-reviewer model: sonnet | Independently reviews one frozen planning artifact for backend feasibility, contracts, data safety, authorization, failure handling, and testability, then performs only assigned finding rechecks. |
| senior-frontend-dev model: sonnet | Senior frontend developer agent handling UI/UX, component architecture, API integration, client state, routing, testing, and performance. Stack-agnostic — adapts to the project's framework and build t |
| senior-frontend-reviewer model: sonnet | Independently reviews one frozen planning artifact for frontend states, component and data flow, API fit, accessibility, responsiveness, and testability, then performs only assigned finding rechecks. |
| senior-tester model: sonnet | Independently verifies the tester's coverage, findings, and conclusions. Can be spawned in parallel with a verification lane focus. Testing is not complete without senior tester sign-off. |
| spec-doc-writer model: sonnet | Transforms requirements into a structured specification with developer documentation — API contracts, data models, and implementation steps — in a single pass for any stack. |
| story-planner model: sonnet | Breaks an approved spec into an ordered, dependency-aware set of small implementable stories, and identifies which can run in parallel. Use when work needs splitting into tickets, sequencing, or a par |
| technical-architect model: sonnet | Reviews a spec or design for architectural soundness — system design, scalability, integration patterns, feasibility, failure modes. Use when a design needs an architecture review before it is built. |
| tester model: sonnet | Validates backend APIs together with the frontend. Verifies API correctness, request/response behavior, UI rendering against spec, integration, error states, and edge cases. Can be spawned in parallel |
| ui-designer model: sonnet | Drafts and self-reviews UI/UX design specs for frontend work. Combines designer and design specialist roles — produces a complete, reviewed design spec in one pass. |
| unit-tester model: sonnet | Writes comprehensive unit test suites for the project. Covers happy paths, edge cases, and error scenarios using the project's test framework. |
Slash commands (4)
/abort/init/sdlc/status
Similar rigs
addyosmani/agent-skills
Production-grade engineering skills for AI coding agents.
Skill Collector 3.7k tok ·
haco29/agentic-sdlc
An agentic SDLC plugin for Claude Code: /spec → /plan → /build → /test → /review → /code-simplify → /pr, with artifacts and gates. Built on addyosmani/agent-skills.
Skill Collector 2.5k tok ·
rizqinrr/viserys-agent
—
Orchestrator 5.3k tok ·
LLl0k0laD/agent-skills
Enhance AI coding agents with structured workflows and best practices for building reliable web applications through production-grade engineering skills.
Skill Collector 2.1k tok ·