hmj1026/dhpk
Reusable Claude Code dev harness plugin — agents, commands, skills, hooks, opt-in stack modules
field: unknown workflow: PR / code reviewTesting & TDDFrontend & designPlanning & specsGit & commits runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 33/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit hmj1026/dhpk/.claude ./rig-dhpk # 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 hmj1026/dhpk/generated/claude-marketplace/package/modules/laravel-10/skills/laravel .claude/skills/laravel $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/modules/library-author/skills/library-author .claude/skills/library-author $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/modules/library-author/skills/openspec-artifact-guard .claude/skills/openspec-artifact-guard $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/modules/phpunit-10/skills/phpunit .claude/skills/phpunit $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/modules/phpunit-5.7/skills/legacy-characterization-tests .claude/skills/legacy-characterization-tests $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/modules/vue-2/skills/vue-2-notes .claude/skills/vue-2-notes $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/change-verdict .claude/skills/change-verdict $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/code-trace .claude/skills/code-trace $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/create-pr .claude/skills/create-pr $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/doc-maintain .claude/skills/doc-maintain $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/flow-drive .claude/skills/flow-drive $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/flow-guide .claude/skills/flow-guide $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/git-smart-commit .claude/skills/git-smart-commit $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/git-worktree .claude/skills/git-worktree $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/harness-setup .claude/skills/harness-setup $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/opsx-apply-resume .claude/skills/opsx-apply-resume $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/precommit .claude/skills/precommit $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/proposal-analyze .claude/skills/proposal-analyze $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/release-creator .claude/skills/release-creator $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/repo-verify .claude/skills/repo-verify $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/tdd-workflow .claude/skills/tdd-workflow $ npx degit hmj1026/dhpk/generated/claude-marketplace/package/skills/ui-ux-verify .claude/skills/ui-ux-verify $ npx degit hmj1026/dhpk/skills/code-simplify .claude/skills/code-simplify $ npx degit hmj1026/dhpk/skills/deploy-list .claude/skills/deploy-list $ npx degit hmj1026/dhpk/skills/feature-verify .claude/skills/feature-verify $ npx degit hmj1026/dhpk/skills/issue-analyze .claude/skills/issue-analyze $ npx degit hmj1026/dhpk/skills/js-static-checks .claude/skills/js-static-checks $ npx degit hmj1026/dhpk/skills/merge-prep .claude/skills/merge-prep $ npx degit hmj1026/dhpk/skills/module-design .claude/skills/module-design $ npx degit hmj1026/dhpk/skills/nextjs .claude/skills/nextjs $ npx degit hmj1026/dhpk/skills/php .claude/skills/php $ npx degit hmj1026/dhpk/skills/pr-summary .claude/skills/pr-summary $ npx degit hmj1026/dhpk/skills/project-audit .claude/skills/project-audit $ npx degit hmj1026/dhpk/skills/project-brief .claude/skills/project-brief $ npx degit hmj1026/dhpk/skills/python .claude/skills/python $ npx degit hmj1026/dhpk/skills/react .claude/skills/react $ npx degit hmj1026/dhpk/skills/repo-intake .claude/skills/repo-intake $ npx degit hmj1026/dhpk/skills/swift .claude/skills/swift $ npx degit hmj1026/dhpk/skills/yii1 .claude/skills/yii1
$ curl -fsSL --create-dirs -o .claude/agents/agy-worker.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/agy-worker.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/codex-reasoner.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/codex-reasoner.md $ curl -fsSL --create-dirs -o .claude/agents/codex-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/codex-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/codex-worker.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/codex-worker.md $ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/database-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/deep-reasoner.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/deep-reasoner.md $ curl -fsSL --create-dirs -o .claude/agents/doc-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/doc-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/docs-lookup.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/docs-lookup.md $ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/fast-worker.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/fast-worker.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/frontend-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/harness-reviser.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/harness-reviser.md $ curl -fsSL --create-dirs -o .claude/agents/migration-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/migration-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-analyzer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/performance-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/python-build-resolver.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/python-build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/qa-executor.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/qa-executor.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/rust-build-resolver.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/rust-build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/silent-failure-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/smoke-tester.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/smoke-tester.md $ curl -fsSL --create-dirs -o .claude/agents/swift-build-resolver.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/swift-build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/tdd-guide.md $ curl -fsSL --create-dirs -o .claude/agents/type-design-analyzer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/type-design-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-ux-verifier.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/ui-ux-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/version-matrix-impact-reviewer.md https://raw.githubusercontent.com/hmj1026/dhpk/main/agents/version-matrix-impact-reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/block-shared-git-stash.js\""
}
]
}
]
}
} Skills (39)
laravellibrary-authoropenspec-artifact-guardphpunitlegacy-characterization-testsvue-2-noteschange-verdictcode-tracecreate-prdoc-maintainflow-driveflow-guidegit-smart-commitgit-worktreeharness-setupopsx-apply-resumeprecommitproposal-analyzerelease-creatorrepo-verifytdd-workflowui-ux-verifycode-simplifydeploy-listfeature-verifyissue-analyzejs-static-checksmerge-prepmodule-designnextjsphppr-summaryproject-auditproject-briefpythonreactrepo-intakeswiftyii1
Subagents (31)
| agy-worker model: sonnet | CLI-backed mechanical implementer — the agy variant of `fast-worker`. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the session |
| architect model: fable | Read-only cross-module architecture work: layer placement, refactor direction, tech debt, interface changes, ADRs, and multi-file plans. Never writes application code. deep-reasoner is also read-only |
| code-reviewer model: sonnet | Expert code review specialist. Recommended for a completed implementation wave or source snapshot that changes source code, or after modifying .claude/ markdown (rules/agents/skills/commands/hooks/scr |
| codex-reasoner model: sonnet | CLI-backed read-only deep-reasoning worker — the codex variant of `deep-reasoner`. Use for root-cause analysis, algorithm design, complex multi-file debugging, and design synthesis during the implemen |
| codex-reviewer model: sonnet | Internal shared-runner Codex review role; capability-gated and not a native Codex dispatch target. |
| codex-worker model: sonnet | CLI-backed mechanical implementer — the codex variant of `fast-worker`. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the shared |
| database-reviewer model: sonnet | Database review specialist (relational + object stores, framework-agnostic). Recommended after writing migrations, SQL queries, Repository methods, or schema changes. Checks prepared statements, index |
| deep-reasoner model: opus | Read-only deep-reasoning worker. Use for root-cause analysis, algorithm design, complex multi-file debugging, and design synthesis during the implement phase — dispatched per the Implementation dispat |
| doc-reviewer model: haiku | >- |
| doc-updater model: haiku | >- |
| docs-lookup model: haiku | REQUIRED for any question about library, framework, SDK, or API usage or current documentation: answers inline and read-only from Context7 docs. Use for how-does-X-work or what-is-the-current-option q |
| docs-writer model: sonnet | Use to edit assigned documentation from confirmed sources; not for refreshing docs made stale by a structural change, inventing product behavior, or claiming runtime acceptance. |
| e2e-runner model: sonnet | Authors, maintains, and runs critical Playwright user-journey tests and stabilizes flaky ones; use proactively when critical journey tests or stabilization are requested. ui-ux-verifier audits one pag |
| fast-worker model: sonnet | Write-capable mechanical implementer. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec — dispatched per the Implementation dispatch tabl |
| frontend-reviewer model: sonnet | >- |
| harness-reviser model: sonnet | Review and improve harness configuration when the user explicitly requests trimming, deduplication, or validation. Output: source-backed findings, scoped fixes, applicable validation, and review evide |
| migration-reviewer model: sonnet | Database migration safety specialist. Reviews schema-migration files for up/down symmetry, idempotency, FK / index naming collision across multi-tenant deploy footprints, large-ALTER strategy on high- |
| performance-analyzer model: sonnet | Performance specialist. Owns latency / index usage / query count for relational data-access (N+1, EXPLAIN, index coverage, query-count regressions) AND — when a frontend or native trap sheet is active |
| planner model: opus | Planner consultant for requested critique, sketch, dual-plan, and manual warm or cold diff review. Follow the caller-provided scope and report actual reads, children, and blockers within the 400-<reda |
| python-build-resolver model: sonnet | Python build-error resolution specialist. Use PROACTIVELY when a Python toolchain command fails — `ruff check` / `ruff format`, `mypy` / `pyright`, `pytest` (incl. pytest-asyncio scope errors), or env |
| qa-executor model: haiku | Live manual QA executor. Runs assigned QA-manual cases against a running environment through a browser skill, records one verdict per case with observed evidence in one assigned results file, and retu |
| refactor-cleaner model: sonnet | Dead-code removal specialist (language-agnostic). Use when files exceed 800 lines, when user explicitly asks to "dedupe" / "remove dead code" / "split file", or during refactor-pass after large featur |
| rust-build-resolver model: sonnet | Rust / Cargo build-error resolution specialist. Use PROACTIVELY when `cargo build` / `cargo test` / `cargo clippy` or dependency resolution fails — rustc type / borrow / lifetime errors, trait-bound a |
| security-reviewer model: sonnet | Read-only security review of a supplied diff after edits, covering input handling, authentication, authorization, uploads, money flows, mobile privacy, and cryptography. code-reviewer covers general q |
| silent-failure-hunter model: sonnet | Error-handling specialist — hunts silent failures: empty catch blocks, swallowed exceptions, error-hiding fallbacks, lost stack traces, and missing error handling around I/O / network / DB / transacti |
| smoke-tester model: sonnet | Read-only live-runtime smoke probe. Drives the REAL running system (deployed daemon, live server, real CLI) with ONE orchestrator-supplied concrete scenario (setup -> trigger -> expected observable ou |
| swift-build-resolver model: sonnet | Swift / Xcode / SwiftPM build-error resolution specialist. Use PROACTIVELY when `swift build`, `xcodebuild`, or SPM dependency resolution fails — compile errors, strict-concurrency / Sendable / actor- |
| tdd-guide model: sonnet | TDD specialist (framework-agnostic). Use PROACTIVELY when writing new features or bug fixes. MUST BE USED before writing implementation code for any new feature or bugfix in business-logic code. Enfor |
| type-design-analyzer model: sonnet | Read-only analysis of invariant-rich domain types: value objects, enums, structs, and data models. Rates how well each type encodes and enforces its invariants. Use when type design is the question; n |
| ui-ux-verifier model: sonnet | UI/UX verification specialist. Drives playwright-cli to capture live A11y snapshots, compares with OpenSpec specs, produces ranked findings, and (with explicit user consent) calls /opsx:new to create |
| version-matrix-impact-reviewer model: sonnet | Specialist for libraries shipping a CI matrix across multiple dependency-version cells (e.g. PHP × Laravel/Symfony, Yii 1×2). Use when editing version-specific source dirs (src/Laravel/, src/Symfony/) |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | node "$CLAUDE_PROJECT_DIR/.claude/hooks/block-shared-git-stash.js" |
Slash commands (20)
/create-pr/create-release/deep-analyze/doc-refactor/flow-drive/flow-guide/git-worktree/matrix-cell-onboard/merge-prep/opsx-apply-resume/pr-summary/precommit/project-brief/setup/simplify/smart-commit/ui-ux-verify/update-codemaps/update-docs/verify
Permissions
deny (0)
—
ask (0)
—
allow (2)
Bash(codex exec:*)
Bash(bash skills/dhpk-codex-bridge/scripts/run-codex.sh:*)
Similar rigs
talayash/agentrium
Native desktop app for running Claude Code, Codex, Cursor, and Antigravity side by side. Tabs, split view, session restore, git worktrees, and agent handoff. Windows and macOS.
MCP Hoarder 37.7k tok · · Q25
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验,集成 MCP 服务器、智能上下文管理、安全扫描,支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok · · Q0
mh2-lee/everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Orchestrator 1.2k tok · · Q3
hirokami3/everything-claude-code
Claude Code configs collection - agents, skills, hooks, commands, rules, and MCP configurations
Orchestrator 1.2k tok · · Q3