By ameenaliu
AI-driven SDLC pipeline on GitHub — Issues + sub-issues + Projects (v2) on a service/web/mobile monorepo. Four-workflow pipeline: discovery-workflow (idea → Epic/Feature/Story/Task tree with hierarchical numbering E1/F1.1/S1.1.1 + Markdown issue bodies + native sub-issue Parent links + native Blocked-by issue dependencies + Project (v2) board membership) → backlog-workflow (refine a Story with issue/body edits, preserves numbering, manages dependencies) → dev-workflow (10-phase build with 3 gates + 3 holistic reviews + Phase 8 architecture/rules reconciliation, two-tier branching, gh PRs) → pr-review (post-PR holistic comments via gh). 4 specialized agents (planner with 5 modes, developer, reviewer with 5 modes incl. gh PR commenting, tester). 7 hooks (4 data-policy + 3 stack quality-check; the secret-scan + pii guards are covered by a hook behavior test suite + GitHub Actions CI). 30 skills total (adds github-rendering canonical structures + sub-issue/dependency protocol, plus capability/quality/security skills the dev/test/review roles drive — auto-installed by /init-workspace: agent-device + maestro-e2e + react-doctor + expo-doctor mobile/web verification, security-scan (Semgrep/Gitleaks/OSV-Scanner), dead-code-analysis (Knip/madge), dotnet-code-quality (Roslynator), bundle-budget (size-limit), migration-safety (EF Core), api-contract-check (oasdiff), observability (Serilog/OTel/Sentry); all advisory). Uses the gh CLI (no MCP server). Works with Claude Code and OpenAI Codex.
[HARNESS INTERNAL — do not invoke directly] Implementation specialist on the in-scope monorepo, activated exclusively by the platform-sdlc-harness dev-workflow orchestrator during Phase 3 (Development Loop). Writes or modifies production code for an approved task across the service/web/mobile surfaces, works through tasks sequentially, ensures builds pass, commits with Conventional Commits (`<type>(<surface>): …`, no issue ID), and follows all coding conventions. Builds, tests, and commits locally only — never runs `gh` or any other remote-write command. Never invoke outside the harness — use /dev-workflow.
[HARNESS INTERNAL — do not invoke directly] Requirements analyst, solution architect, idea decomposer, story refiner, and architecture-rules auditor. Activated exclusively by the platform-sdlc-harness workflows in 5 modes: `requirements` (dev-workflow Phase 1), `plan` (dev-workflow Phase 2), `architecture-audit` (dev-workflow Phase 8), `discovery` (discovery-workflow D1/D2/D3/extend — shape idea into Epic→Feature→Story→Task tree), and `refinement` (backlog-workflow — enrich a single Story via GitHub Issue body edits + Comments). All GitHub reads/writes go through the `gh` CLI / `gh api graphql` invoked via Bash — there is no MCP server. Never invoke outside the harness — use /discovery-workflow, /backlog-workflow, or /dev-workflow.
[HARNESS INTERNAL — do not invoke directly] Code quality gatekeeper, activated exclusively by the platform-sdlc-harness dev-workflow orchestrator in five modes: per-task review (Phase 3), holistic pre-test review (Phase 4), per-test-task review (Phase 6), holistic pre-PR review (Phase 7), and post-PR review with GitHub PR comments (Phase 10). Evaluates code quality, conventions compliance, and correctness against the approved plan. Read-only for source code; in Phase 10 also posts inline + summary comments to the open GitHub PR via the `gh` CLI (`gh api` PR review comments + `gh pr review --comment`) invoked through Bash — there is no MCP server. Returns a structured review report to the orchestrator. Phase 10 is comment-only — never blocks the PR. Never invoke outside the harness — use /dev-workflow or /pr-review.
[HARNESS INTERNAL — do not invoke directly] Test implementation specialist on the in-scope monorepo, activated exclusively by the platform-sdlc-harness dev-workflow orchestrator during Phase 6 — after all development tasks are approved AND GATE #2 (post-Phase-4 holistic review) is crossed. Writes unit and integration tests for the service surface (xUnit + FluentAssertions + Moq + Testcontainers + WebApplicationFactory + Refit), web surface (Vitest + React Testing Library + MSW), and mobile surface (Jest + @testing-library/react-native). Commits with `test(<surface>): …` Conventional Commits (no issue ID). Builds, tests, and commits locally only — never runs `gh` or any other remote-write command. Never invoke outside the harness — use /dev-workflow.
<!--
Drive a real iOS/Android app on a simulator, emulator, or device to verify MOBILE changes in the agentic build→run→inspect→fix loop. Load this when implementing or debugging an Expo / React Native screen and you need to confirm the running UI behaves as intended — not just that it compiles. Wraps the `agent-device` CLI (Callstack): a token-efficient way for an agent to open the app, read a compact accessibility snapshot, tap/type on real elements, and capture screenshots / logs / performance evidence.
Detect breaking API changes on the SERVICE surface before a PR ships, by diffing the OpenAPI/Swagger spec of the change against the base branch with oasdiff. In a service↔web↔mobile monorepo a silently-broken endpoint contract breaks consumers at runtime — this catches removed endpoints, removed/renamed fields, newly-required parameters, and type changes. Load this in the Reviewer Phase B (and Developer self-review) for SERVICE tasks that touch controllers, DTOs, or routing. Advisory — surfaces breaking changes; never auto-blocks.
Refine, analyze, improve, and enrich GitHub Story issues with structured templates, surface-aware quality checks (E/F/S numbering prefix, Surface label, parent Feature), and codebase-aware technical analysis driven by `.claude/architecture/*` + `.claude/rules/*` in the configured repo. Outputs land in the Story issue itself as Title / body / Acceptance criteria edits + change-log comments. Use this skill whenever the user mentions Story refinement, enrichment, analysis, or improvement, acceptance criteria, Story quality, sprint readiness, or commands like /backlog-improve, /backlog-refine, /backlog-analyze, /backlog-enrich. Also trigger when the user references GitHub issue numbers in the context of improving or reviewing Story quality. This skill is never invoked autonomously — it only runs when explicitly requested by a human user.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
A GitHub-native Claude Code + Codex plugin marketplace, designed to be installed once and shared across projects. It ships two plugins:
platform-sdlc-harness — a multi-agent SDLC workflow (orchestrator → planner / developer / reviewer / tester) with 3 human approval gates and 3 holistic review phases, driven by GitHub Issues + sub-issues + Projects (v2) and the gh CLI (no MCP server). Lifecycle: Epic → Feature → Story → Task; two-tier branching; Conventional Commits; gh PRs.platform-product-video-harness — Remotion + ElevenLabs product-video generation + multilingual localisation for social media, with a per-project brand kit.Both are stack-flexible (defaults: .NET 8 service/ + React 19 Turbo web/ + Expo mobile/) and configured per-repo by /init-workspace into .claude/context/.
Works with two AI coding tools. The plugins are the canonical source; running the relevant init scaffolds the equivalent setup for OpenAI Codex as well as Claude Code, so a team runs the same workflow + conventions whichever tool they use. A data-policy layer (hooks in Claude; AGENTS.md rules + optional pre-commit/CI guards elsewhere) keeps PII, customer data, and credentials away from the model.
The marketplace lives on GitHub at ameenaliu/harness-platform.
.claude/settings.jsonCommit this to a project repo's .claude/settings.json so every teammate gets the marketplace auto-registered and the plugins enabled when they open the repo in Claude Code (one-time trust prompt):
{
"extraKnownMarketplaces": {
"harness-platform": {
"source": { "source": "github", "repo": "ameenaliu/harness-platform" },
"autoUpdate": true
}
},
"enabledPlugins": {
"platform-sdlc-harness@harness-platform": true,
"platform-product-video-harness@harness-platform": true
}
}
/plugin marketplace add ameenaliu/harness-platform
/plugin install platform-sdlc-harness@harness-platform
/plugin install platform-product-video-harness@harness-platform
/init-workspace
type:*, surface:*, status:*) and the org Project (v2) board exist;.claude/context/platform-context.md + .claude/settings.local.json;AGENTS.md, .codex/agents/*.toml, .agents/skills/platform-*-workflow/ — so Codex runs the same workflow.| Requirement | Notes |
|---|---|
gh CLI | Authed (gh auth status) with scopes repo, project, read:org, workflow. |
| Stack toolchains | Per adopted surface: .NET 8 SDK (service), Node 20+/Yarn 4 (web), Expo/Node (mobile). |
| ffmpeg + ElevenLabs key | Only for the product-video plugin. |
harness-platform/
.claude-plugin/marketplace.json # 2 plugins
plugins/
platform-sdlc-harness/ # SDLC pipeline (GitHub Issues + Projects + gh)
platform-product-video-harness/ # Remotion + ElevenLabs videos (per-project brand)
scripts/ # marketplace maintenance (validate, conflicts, context-bloat)
README.md AGENTS.md LICENSE
See each plugin's README.md and CLAUDE.md for the full rules and workflows.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimExecutes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI-driven product-video generation + multilingual localisation for social media. Brand-agnostic — each project supplies its own brand kit (collected per-workspace into <ProductVideos>/brand/brand.json). Four user-invocable skills: init-video-workspace (one-time setup + brand kit collection), generate (5-phase pipeline + Phase 0 brief drafting + 3 human approval gates + V8 animation-pacing + V9 callout-alignment vision review), translate (re-render captions + re-synthesise voiceover; ElevenLabs for en + 31 other languages; 9jaLingo for yo/ha/ig/pcm; captions-only fallback otherwise), update-brand-kit (refresh colors/logo/tagline/fonts/personas anytime). Pipeline: optionally extracts frames from a sample via ffmpeg + Claude vision; selects from 6 markdown script templates; composes Remotion .tsx that renders to 9:16 + 1:1 + 16:9 in one pass; generates voiceover + ambient bed via ElevenLabs (Starter $5/mo, commercial-licensed); muxes audio + video via ffmpeg into 3 final MP4s. 5 specialised agents (analyzer, scriptwriter, compositor, narrator, reviewer). 4 hooks (secrets-guard for sk_ + nl- + .env protection, large-media-guard, render-quality-check, pii-pattern-guard). 18 skills total (4 user-invocable + 3 conventions + brand-collection + 9jalingo-voices + 9 supporting). Credentials live in <ProductVideos>/.env (gitignored, hook-protected). The ProductVideos workspace is a local folder, optionally backed by a GitHub repo you supply. Works with Claude Code and OpenAI Codex.
npx claudepluginhub ameenaliu/harness-platform --plugin platform-sdlc-harnessComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques