By iamcxa
Autonomous nightly improvement — forge validation, multi-source signal discovery (journal, Sentry, E2E, git), north-star-aligned proposals and alerts
Scan E2E test reports for failure trends, coverage gaps, and stale mappings. Returns structured YAML with confidence-rated findings. Dispatched by kc-nightwatch orchestrator during Phase 2 for targets with `e2e-reports` in sources. <example> Context: kc-nightwatch orchestrator needs E2E signals for my-app user: "Scan E2E reports for my-app. Path: ~/Project/my-app. Keywords: [checkout, order]. North star: Checkout flow completes with zero friction. Proxy signals: e2e-coverage." assistant: "Scanning E2E report directories for failure trends and coverage gaps." <commentary>Scans .claude/e2e/ and e2e-reports/ for test results and mapping staleness.</commentary> </example> <example> Context: kc-nightwatch orchestrator scans a project with no E2E infrastructure user: "Scan E2E reports for my-service. Path: ~/Project/my-service. Keywords: [api, validation]. North star: API validation with zero config. Proxy signals: validation-coverage." assistant: "No e2e-reports/ or .claude/e2e/ directories found — returning empty signals." <commentary>Graceful with missing dirs: projects without E2E infrastructure get empty signals, not errors.</commentary> </example>
Analyze git history for churn hotspots and long-untouched code areas. Returns structured YAML with confidence-rated findings. Dispatched by kc-nightwatch orchestrator during Phase 2 for targets with `git-stats` in sources. <example> Context: kc-nightwatch orchestrator needs git stats for my-app user: "Scan git stats for my-app. Path: ~/Project/my-app. Keywords: [checkout, order]. North star: Checkout flow completes with zero friction. Proxy signals: checkout-friction." assistant: "Analyzing git log for high-churn hotspots and stale code areas." <commentary>Uses git log --since for commit frequency analysis by directory.</commentary> </example> <example> Context: kc-nightwatch orchestrator scans a plugin repo (not a product) for git churn user: "Scan git stats for kc-pr-flow. Path: ~/Project/my-workspace/kc-pr-flow. Keywords: [PR, review, create-pr]. North star: PR lifecycle from creation to review response. Proxy signals: skill-coverage, review-friction." assistant: "Analyzing git log for high-churn skill files and stale references." <commentary>Git scanner works on any git repo, including plugin repos — not limited to product targets.</commentary> </example>
Scan Sentry for production error signals — new issues, error spikes, regressions. Returns structured YAML with confidence-rated findings. Dispatched by kc-nightwatch orchestrator during Phase 2 for targets with `sentry` in sources. <example> Context: kc-nightwatch orchestrator needs Sentry signals for my-app user: "Scan Sentry for my-app. Project: my-app-web. Keywords: [checkout, order, payment]. North star: Checkout flow completes with zero manual intervention. Proxy signals: checkout-friction, error-rate, e2e-coverage." assistant: "Searching Sentry project my-app-web for production error signals." <commentary>Dispatched for targets with sentry in sources and sentry_project configured.</commentary> </example> <example> Context: kc-nightwatch orchestrator needs Sentry signals but MCP tools are unavailable user: "Scan Sentry for my-service. Project: my-service-api. Keywords: [api, auth, webhook]. North star: API reliability above 99.9%. Proxy signals: error-rate." assistant: "Sentry MCP tools not available — returning empty signals with warning." <commentary>Graceful degradation: when Sentry MCP tools fail, return empty YAML with warning instead of erroring.</commentary> </example>
Search journal, episodic memory, and MEMORY.md for plugin improvement signals aligned with north star goals. Returns structured YAML with confidence-rated findings. Dispatched by kc-nightwatch orchestrator during Phase 2 (Signal Harvest). <example> Context: kc-nightwatch orchestrator is running Phase 2 and needs improvement signals for kc-pr-flow user: "Harvest signals for kc-pr-flow. Keywords: [PR, review, pr-flow, create-pr, code review]. North star: PR lifecycle from creation to review response. Proxy signals: skill-coverage, review-friction. Plugin path: ~/Project/my-workspace/kc-pr-flow. Repo: my-plugins." assistant: "Searching journal, episodic memory, and MEMORY.md for kc-pr-flow improvement signals." <commentary>Phase 2 dispatches one harvester per plugin with keywords and north star context from nightwatch-targets.yaml.</commentary> </example> <example> Context: kc-nightwatch orchestrator needs signals for e2e-pipeline (different repo) user: "Harvest signals for e2e-pipeline. Keywords: [e2e, browser test, mapping, walkthrough, flow, selector]. North star: Browser E2E testing is fully automated. Proxy signals: mapping-freshness, flow-coverage, pipeline-friction. Plugin path: ~/Project/my-workspace/e2e-pipeline. Repo: my-plugins." assistant: "Searching all three sources for e2e-pipeline improvement signals." <commentary>Harvester works the same regardless of which repo the plugin is in — repo field is passed through to output.</commentary> </example>
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
v2.6.0Browser & 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, and record CLI-only flows via terminal recording (asciinema).
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
v1.7.0One-command plugin quality pipeline. Validates structure, TDD-tests skills under pressure, smoke-tests skills in clean profile (--bare mode, ~$0.025/test), 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.
Use when: You're building or maintaining Claude Code plugins and want automated quality assurance.
Prerequisites: superpowers + plugin-dev marketplace plugins.
/plugin install kc-plugin-forge@kc-claude-plugins
v0.4.0Autonomous 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
v1.3.0Session lifecycle & context efficiency. Detects context pressure and enforces cleanup before session end. Cross-session handoff/resume via journal entries with one-command restore. Context Lake (SQLite FTS5) caches codebase insights for faster exploration. Includes a standalone statusline with Anthropic 5h/7d usage quota display.
| 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
Add to .claude/settings.json:
{
"extraKnownMarketplaces": {
"kc-claude-plugins": {
"source": {
"source": "github",
"repo": "iamcxa/kc-claude-plugins"
}
}
},
"enabledPlugins": {
"e2e-pipeline@kc-claude-plugins": true,
"kc-plugin-forge@kc-claude-plugins": true,
"kc-nightwatch@kc-claude-plugins": true,
"kc-hyperfocus@kc-claude-plugins": true
}
}
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
Session 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 E2E testing pipeline with context-isolating subagents — map UI, run tests, walk through apps, record video
Paydirt multi-agent orchestrator with Goldflow execution engine
npx claudepluginhub iamcxa/kc-claude-plugins --plugin kc-nightwatchRun 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
Audit Claude Code plugins and skills for best practices, deprecations, compatibility, usability, coverage gaps, duplication, and workflow optimization
Agents specialized in quality assurance, testing strategies, and test architecture. Focuses on ensuring code quality and reliability.
DevsForge Enterprise Testing Automation Architect delivering comprehensive testing methodologies, quality assurance frameworks, and automated testing strategies that transform testing from validation function into strategic business value creation and development excellence catalyst