claude-harnesses

Umbrella plugin bundling every skill, command, agent, and hook from all claude-harnesses packs in one install.

Severity-ranked code review and multi-pass security review with parallel specialist subagents.

Watch PRs after creation: monitor CI, dispatch fixes via subagents, address review feedback, and report.

Red-Green-Refactor TDD with subagent context isolation between test writer, implementer, and refactorer.

Deterministic PreToolUse guards: secret detection, dangerous command blocking, branch protection, prompt-injection detection, and MCP tool allowlisting.

Verification feedback loop: format/typecheck/test on every edit, and block premature Stop until scripts/verify.sh passes.

Survive context loss across sessions: SessionStart context injection, cost-ceiling, large-edit gate, session-end summary, ledger templates, and goal-manager workflow.

Route an independent, review-only Claude process to a deterministically stronger model or effort when native Advisor is unavailable.

Compatibility alias for pr-guardian. Use pr-guardian for stalled pull requests, CodeRabbit/Codex review feedback, CI failures, unresolved review conversations, and merge-ready PR follow-up.

Diagnose and repair failing CI checks on the current PR by parsing logs, reproducing locally when possible, and pushing focused fixes in batches.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.

Run an end-to-end Claude Code delivery workflow from user request to merge-ready pull request, including planning, implementation, tests, self-review, ready-for-review PR creation, CI/review follow-u…

Fetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown.

"Run a continuous product improvement loop: evaluate a product or codebase, present prioritized recommendations for approval, then implement only approved improvements through verification and PR fol…

Analyze recent Claude Code work and package repeated patterns as the smallest useful skill, custom subagent, slash command, hook, or automation.

Monitor a pull request after opening it or resume a stalled PR, fix CI failures and reviewer feedback, push updates, reply to and resolve review conversations, and comment with the outcome.

Review code changes with a bug-first, risk-focused workflow before merge or release.

Prepare a human reviewer to review a pull request in the least time with the best judgment.

Run a multi-pass security review over the current diff using parallel specialist subagents focused on injection, authn/authz, secrets, supply-chain, and infrastructure-as-code risks.

Drive development with red-green-refactor using isolated test-writer, implementer, and refactorer subagents so tests reflect intent rather than anticipated implementation.

Teach the human everything that happened in this session until they can demonstrably explain it, using an incremental checklist, restate-first probing, and AskUserQuestion quizzes.

Direct high-quality frontend UI work by using image-generated mockups when useful, translating the chosen direction into code, and verifying the rendered UI in a browser.