By iamcxa
PR lifecycle workflow: create, review, resolve reviews, commit reorg, automated daemon, and break-point runtime-path probes.
Audits GitHub Actions workflows for AI agent security vulnerabilities — env injection, expression injection, dangerous sandbox, wildcard allowlists. Dispatched by kc-pr-review when workflow files change.
Security-focused differential review of PR diffs. 6-phase analysis — risk triage, blast radius, adversarial modeling, attack scenarios. Dispatched by kc-pr-review for security-tier PRs.
Audits dependency changes for supply chain risk and insecure defaults. Checks maintainer health, CVE history, fail-open patterns. Dispatched by kc-pr-review when dependency files change.
Use when verifying that a fix actually reaches the bug's break-point in the real runtime path — not just at unit-test level. Primary trigger is bugfix / cross-stack PR review (invoked by kc-pr-review). Also invoke standalone when pressure-testing a fix claim, pre-merge verification of cross-layer wiring, or debugging "why is this still broken". Output is a strict YAML contract declaring precision level (A/B/C/D), verified vs unverified failure-chain steps, residual uncertainty, and recommended human probes. Designed to prevent silent verification failure where an agent reports "verified" without actually exercising the runtime path.
Use when a feature is complete with PR and demo artifacts (e2e walkthroughs, Loom, screenshots), and user wants to announce on Slack. Triggers on "announce", "post to product", "draft product message", "公告", or after PR + demo completion.
Use when user says 'create pr', 'open pr', '建立 PR', '開 PR', '發 PR', '送審', or when implementation is complete and changes need a pull request on GitHub.
Use when user says 'start daemon', 'stop daemon', 'daemon status', 'pr daemon', 'daemon config', 'daemon 掛了', 'daemon error', '啟動 daemon', '停止 daemon', 'daemon 狀態', or wants to manage, configure, or troubleshoot the PR review closed-loop daemon.
Use when a feature branch has messy interleaved commits that need reorganization into logical groups before PR review. Triggers include "squash commits", "clean up history", "reorganize commits", "reorder commits", "too many commits". Not for simple squash-all — use git merge --squash instead.
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.
Claude Code plugin marketplace by Kent Chen.
/plugin marketplace add iamcxa/kc-claude-plugins
Browser & CLI E2E testing with context-isolating subagents. Map your app's UI, generate test flows from plans, verify in browser with auto-repair, run tests with video recording, record CLI-only flows via terminal recording (asciinema), and verify static UI computed styles via the new declarative /ui-verify skill. Codex platform manifest ships alongside Claude Code.
Use when: You need automated browser or CLI testing for a web app — from first mapping to CI integration.
Prerequisite: agent-browser CLI installed globally.
/plugin install e2e-pipeline@kc-claude-plugins
One-command plugin quality pipeline. Validates structure, TDD-tests skills under pressure (or via skill-creator benchmarking with --use-skill-creator), audits SKILL.md frontmatter against the official Claude Code spec (Phase 2.4), smoke-tests skills in clean profile (--bare mode, ~$0.025/test), optionally optimizes skill descriptions for trigger reliability (Phase 2.6 via --optimize-desc), verifies agent definitions, detects Agent Teams capability, and scaffolds self-improvement (D1/D2 learning) and doc-sync capabilities. Supports --parallel mode for concurrent Phase 2/3 execution via teammates. Codex platform manifest ships alongside Claude Code.
Use when: You're building or maintaining Claude Code plugins and want automated quality assurance.
Prerequisites: superpowers + plugin-dev marketplace plugins. Optional: skill-creator for --use-skill-creator and --optimize-desc modes.
/plugin install kc-plugin-forge@kc-claude-plugins
Autonomous nightly plugin improvement cycle. Runs forge validation, harvests signals from journal/Sentry/E2E/git, and generates improvement proposals aligned to north-star goals.
Use when: You want continuous, automated quality monitoring across your plugin ecosystem.
/plugin install kc-nightwatch@kc-claude-plugins
Session lifecycle & context efficiency. Detects context pressure and enforces cleanup before session end. Cross-session handoff/resume via integrated journal (with vector embedding search via MiniLM). Context Lake (SQLite FTS5) caches codebase insights for faster exploration. MCP context firewall: the mcp-summarizer subagent keeps raw payloads from Linear/Sentry/Notion/Supabase/Figma/Slack/Langfuse out of main context, and a PreToolUse nudge proactively suggests it on first read-op per MCP family per session. Includes a standalone statusline with Anthropic 5h/7d usage quota display. Cross-platform install verified by CI matrix (linux-x64, darwin-arm64, darwin-x64) via the new postinstall verify step.
| Skills | Purpose |
|---|---|
/kc-session-handoff | Write journal + produce resume prompt with handoff ID |
/kc-session-resume | Restore context from journal handoff entry (O(1) with ID) |
/kc-cache-insight | Manual cache insight + lake status + metrics view |
/kc-statusline-setup | Install statusline with model, branch, context bar, usage quota |
Use when: You want automatic context pressure warnings, enforced session handoff, cross-session context restoration, and codebase insight caching.
Requires: bun runtime (for Context Lake MCP server and hooks).
/plugin install kc-hyperfocus@kc-claude-plugins
Team operations pipeline for engineering managers. EM triage with strategic lens (depth-adaptive routing, team context cache), project pulse updates, codebase exploration, issue decomposition, structured Linear management, and cross-model second opinion via Google's agy / Antigravity CLI (/gemini review|challenge|consult — same usage as /codex, routed through Google's agy for a non-OpenAI outside voice; participates in a gstack cross-model review dashboard when gstack is installed).
Use when: You're an EM running triage on Linear issues, drafting weekly pulse updates, decomposing oversized issues with team context, or want an independent cross-model review / adversarial challenge / consult from Gemini.
Prerequisite: Linear MCP enabled.
/plugin install kc-team-ops@kc-claude-plugins
npx claudepluginhub iamcxa/kc-claude-plugins --plugin kc-pr-flowOne-command plugin development and quality pipeline — scaffold, TDD skills, verify agents, validate structure, doc self-iteration
Autonomous nightly improvement — forge validation, multi-source signal discovery (journal, Sentry, E2E, git), north-star-aligned proposals and alerts
Session lifecycle & context efficiency plugin: context pressure detection, cleanup enforcement, cross-session handoff/resume, MCP context firewall, context lake cache, journal, and statusline.
Browser & CLI E2E testing pipeline with context-isolating subagents — map UI, generate flows, verify & test, walk through apps, record video, terminal recording for CLI-only flows, static UI computed-style verification
Paydirt multi-agent orchestrator with Goldflow execution engine
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows