Plugins

Claude Code 하네스 진화 도구: CLAUDE.md(규칙 전달) + Permissions(위험 차단) + Hooks(자동 검증) + MCP(테스트 도구) + Subagent(AI 분리) + 진화 원칙(메타) 6단계를 진단·추천·확정 워크플로우로 단계적으로 보강합니다. 신규 셋업보다는 이미 쓰는 프로젝트의 하네스를 진화시키는 데 초점. 1개 스킬.

Tiered autonomy + build-test-fix, staged dev, and prod deploy loops for hands-off AI workflows

Coding harness for long-term tasks, based on @claude article harness-design-long-running-apps

크로스 플랫폼 AI 에이전트 하네스

Warn-only, zero-dependency runtime harness layer for Claude Code (companion to superpowers): persistent state, scope control (prompt + action side), Default-FAIL verification & coverage gates, entropy governance (golden-rules + drift detection), and first-class C/C++ engineering (CMake/Meson/Make/Bazel + clang-tidy + sanitizers).

Four non-negotiable safety hooks plus cross-cutting engineering modules as auto-loading skills. Every domain pack depends on this.

v1.0.1 | 개발 중간에 에이전트 제어 인프라(훅, verifier, 문서 자동화) 상태를 독립 서브에이전트가 진단하고, 문제 발견 시 upstream 수정 레포트를 생성하는 하네스 점검 스킬

Three defense-in-depth hooks: credential value scrub (PostToolUse), admission keyword reminder (UserPromptSubmit), bash command guard (PreToolUse). Built after repeated credential leak incidents — structural fix when behavioral rules in CLAUDE.md keep failing.

Curated data pack: analytics engineering, analyst notebook, LLM app, ML pipeline.

Authoring aids for building Claude Code harnesses — loops, flows, and the specs that separate them.

Curated devops pack: CI/CD platform, infrastructure, Kubernetes platform, observability/SRE.

Evaluate AI agent setups for best practices, redundancy, security, and cross-component issues. 64 lint rules, per-component rubric review, deep security audit, and single-skill evaluation.

LangSmith-native autonomous agent optimization — evolves LLM agent code using multi-agent proposers, experiments, and git worktrees. No external API keys needed.

HarnessFlow v3.0.0: 7 core skills own the risk-tiered main chain frame -> plan -> build -> verify -> ship (hf-workflow entry, hf-frame with environment baseline, hf-plan, hf-build TDD, hf-verify runtime smoke, hf-review with independent-context discipline, hf-ship). A stdlib-only mechanical gate (skills/hf-workflow/scripts/hf_gate.py) produces tamper-evident evidence logs and adjudicates every stage transition from files, verdict lines, exit codes and timestamps. Domain skills plug in as ext-* extensions loaded per stage (ext-ui-design and ext-cpp ship as seeds).

Peer-pane Claude Code worker orchestration via tmux + jsonl mailbox. Spawns long-running coordinated workers from natural-language triggers. Bundles formation skill + njslyr7 CLI + UserPromptSubmit hook that auto-suggests the skill when user prompts match worker-spawn intent. Session-scoped identity prevents mailbox drift across resume/compact.

Workflow stage machine, convergence/workflow/experiment loops, local-LLM agents, memory, MCP, and a metrics dashboard.

Three-perspective preflight review skill (MELCHIOR/BALTHASAR/CASPAR personas, parallel Task spawn) for high-stakes changes — front-loads post-hoc optimization insights before walltime / cost / destructive state is committed. Triggers on walltime >= 2h, >= 100M row DML, non-reversible cutover, new pipeline layer, >= $10 spend, or long-poll scripts.

Curated mobile pack: native iOS, native Android, React Native + Expo, Flutter.

Operational safety rails for long-running operations. Pre-flight algorithm fitness CLI (working set vs RAM ceiling, with concrete alternatives), in-flight heartbeat helper + cron watcher (stale + ETA overrun detection), Discord + gh issue auto-emit. Human-in-loop only — no auto-kill. Built after a 23h sunk-cost incident where philosophy-level early-bleeding-detection lived only in CLAUDE.md memory, not in structural rails.

Automatic security analysis on file edit and save. Analyze code for vulnerabilities (SOURCE → FLOW → SINK) and reports findings back so Claude can fix them.

Curated web pack: API service, design system, distributed backend, frontend app, fullstack app.

Claude Code plugin for email triage, calendar management, and CRM integration via MCP servers.

Harvester HCI operator suite — controlled, community-edition Harvester upgrades off an EOL line up to latest stable: the no-skip minor ladder (1.5→1.6→1.7→1.8 carrying embedded RKE2 / KubeVirt / Longhorn / SLE-Micro together), external-Rancher + Harvester UI-extension pairing and ordering, air-gapped version detection, controlling the node-by-node upgrade flow (serial interlock, the v1.7+ pause-map, and the PodDisruptionBudget + VMI-readinessProbe native gate for 1.5/1.6), keeping VM-hosted self-managed RKE2 control planes quorate via anti-affinity spread and live-migration-vs-clean-shutdown tradeoffs (busy-etcd non-convergence, auto-converge, dedicated migration network), per-hop breaking changes (wicked→NetworkManager, Intel NIC rename, DHCP churn), the enforced pre-flight health gates, and the no-downgrade backup/rollback reality. Companion to the k8s suite's k8s-components-checker (Harvester↔Rancher↔RKE2 pairing registry) and rancher-upgrade (the external Rancher's own chain).

ステージされていない変更を検出し、適切なコミット粒度の提案からgit commitまでを一貫してアシストするスキル

from TheBushidoCollective/han

Plugin from ncaq/konoka

Default Claude Code setup — memory lifecycle hooks, codebase exploration, builder/reviewer agents, and git hook automation

Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.

Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.

Configure HawkScan in your CI/CD pipeline. Provider-agnostic: detects GitHub Actions, GitLab CI, Jenkins, CircleCI, Azure Pipelines, Bitbucket, Buildkite, and other CI systems from repo files, edits the pipeline file in place, and prompts for HAWK_API_KEY storage (CI-native secrets store or external secrets manager).