By luciferdono
Production-grade code quality, review, CI management, and branch workflow skills with subagent-driven architecture. Enforces sole authorship, humanized commits, and systematic best-practice auditing.
Diagnose and fix failing CI checks on the current branch
Review an implementation plan or design doc against project conventions
Create or update a pull request with preflight checks
Run pre-submission checks (lint, test, build) before opening a PR
Run a best-practice code review on the current diff or PR
Check and fix milestones on PRs and their associated issues. Sets PR milestones based on the branch they merged into, and issue milestones based on the smallest version with a merged fix. Triggers on: check milestones, fix milestones, /check-milestones.
Delete local branches whose PRs have been merged upstream. Checks GitHub PR status for each branch. Triggers on: clean branches, delete merged branches, prune branches, branch cleanup.
Force-push a branch and all its downstream branches to origin. Auto-detects the downstream tree and skips branches already up-to-date. Triggers on: force push downstream, push chain, push all branches.
Implement review feedback on a PR. Checks out the branch, applies reviewer-requested changes, runs preflight, commits, and pushes. Triggers on: impl-review, implement review, implement review feedback, address review comments.
Re-run failed GitHub Actions CI jobs for a PR. Detects failure type (build vs test) and reruns only failed jobs. Triggers on: make ci green, retry ci, rerun ci, fix ci, re-run failed jobs, retrigger ci.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
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 claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that enforces code quality, sole authorship, and review discipline across your contributions.
/review) -- Best-practice code review using parallel subagent chunks. Audits your diff against a full ruleset and reports violations with file, line, severity, and draft comments./pr) -- Create or update pull requests with built-in preflight checks and style-matched descriptions./ci) -- Diagnose and fix failing CI checks on your current branch./preflight) -- Run lint, test, and build checks locally before opening a PR./impl-review) -- Review an implementation plan or design doc against project conventions.Co-Authored-By, Generated with).claude plugin add LuciferDono/sentinel
/review
Review only a specific file or path:
/review src/parser.ts
/pr
Target a specific base branch:
/pr --base develop
/ci
/preflight
/impl-review docs/design.md
The /review command splits the full best-practice ruleset into chunks and launches a code-reviewer subagent for each chunk in parallel. Each subagent:
The parent skill collects all subagent results, deduplicates findings, and produces a single consolidated report. This approach scales linearly with ruleset size without hitting context limits.
The PreToolUse hook in hooks/hooks.json intercepts every Bash tool call. If the command contains Co-Authored-By or Generated with, the hook exits with code 1 and the commit is blocked. This enforces sole authorship on all commits made through Claude Code.
MIT
Lazy-loading ECC fork — full Claude Code enhancement suite with on-demand component loading via registry-driven auto-detection
End-to-end academic research paper writing plugin. Covers the complete lifecycle from ideation through post-publication: literature review, novelty verification, research design, data management, paper architecture, writing, verification, venue selection, formatting, peer review response, camera-ready, and dissemination. Supports all paper types (journal, conference, workshop, thesis, survey, demo, dataset, book chapter) across all disciplines (CS, medicine, social sciences, humanities, business). Includes AI policy management, collaborative writing workflows, and persistent session intelligence.
npx claudepluginhub luciferdono/sentinelHarness-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
Comprehensive 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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.