By iamcxa
Autonomous nightly improvement — forge validation, multi-source signal discovery (journal, Sentry, E2E, git), north-star-aligned proposals and alerts
Scans E2E test reports for failure trends, coverage gaps, and stale mappings. Returns confidence-rated YAML. Dispatched by kc-nightwatch (Phase 2) for targets with `e2e-reports` in sources. Graceful when no e2e infrastructure.
Analyzes git history for churn hotspots and long-untouched code areas. Returns confidence-rated YAML. Dispatched by kc-nightwatch (Phase 2) for targets with `git-stats` in sources. Works on any git repo.
Scans Sentry for production error signals (new issues, spikes, regressions). Returns confidence-rated YAML. Dispatched by kc-nightwatch (Phase 2) for targets with `sentry` in sources. Graceful when MCP unavailable.
Searches journal, episodic memory, and MEMORY.md for plugin improvement signals aligned with north star goals. Returns confidence-rated YAML. Dispatched by kc-nightwatch (Phase 2).
Use when setting up, configuring, or managing kc-nightwatch scheduling and settings. Triggered by '/kc-nightwatch-config', or when user asks to schedule nightwatch, change cron time, configure Slack channel, or check what plugins are monitored.
Use when checking nightwatch status, viewing last run results, reviewing improvement history, or reviewing pending proposals. Triggered by '/kc-nightwatch-report', '/kc-nightwatch-report --last', '/kc-nightwatch-report --review', or asking about nightwatch activity.
Use when running nightly plugin improvement cycle — forge validation, signal harvesting, north-star gap analysis, auto-fix and proposal generation. Triggered by cron or manual invocation.
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-nightwatchSession lifecycle & context efficiency plugin: context pressure detection, cleanup enforcement, cross-session handoff/resume, MCP context firewall, context lake cache, journal, and statusline.
One-command plugin development and quality pipeline — scaffold, TDD skills, verify agents, validate structure, doc self-iteration
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
PR lifecycle workflow: create, review, resolve reviews, commit reorg, automated daemon, and break-point runtime-path probes.
Paydirt multi-agent orchestrator with Goldflow execution engine
Code quality and validation: clone detection, multi-agent E2E validation, performance profiling, schema testing
Run Claude autonomously for 6-8 hours overnight using Git hooks that enforce TDD - wake up to fully tested features
Skill evaluation and benchmarking - test skill effectiveness with behavioral eval cases, grade results, and track quality improvements
Quality assurance - E2E testing, PR review, browser automation
PLAN/ACT/EVAL workflow with auto-detection, specialist agents, and reusable skills for systematic TDD development
Audit Claude Code plugins and skills for best practices, deprecations, compatibility, usability, coverage gaps, duplication, and workflow optimization