gsd
claudePhase-based dev framework: roadmaps, plans, execution, verification, debugging.
57 commands · 18 agents
Bug/cleanup/deps/reuse/security health audits, security audit, threat hunting, finding and vetting third-party skills before install.
Plugin code-health from marketplace hamidun in JHamidun/claude-code-config-pack. Commands read from the repo's manifest — 26 days ago.
config-healthЗдоровье конфига Claude Code: битые ссылки, вес промпта, лимит памяти, живость MCP. Триггеры: «проверь конфиг», «вес промпта». НЕ чужой скилл→skill-manager; НЕ код→health-inline
health-inlineЧинит codebase health инлайн: /health bugs|cleanup|deps|reuse|security — детекция→фикс→верификация. Только pnpm+TypeScript-репо. НЕ одна красная сборка→build-fix.
leak-scanPII/деанон перед публикацией (leak_scan.py) + prompt-injection в чужом скилле (skill_injection_scan.py). Триггеры: «обезличь репо», «проверь скилл перед установкой».
osint-reconРазведка инфраструктуры домена/IP CLI osint_client.py: DNS, whois, субдомены, порты/CVE, санкции. Триггеры: «пробей домен». НЕ люди→social-intel.
privacy-filterЛокальный PII-фильтр (OpenAI opf, on-device): обезличить текст перед облачным LLM, обратимая редакция. Триггеры: «обезличь текст», «найди ПД».
security-auditSecurity-аудит: секреты в коде, pip/npm audit, OWASP Top 10. Триггеры: «аудит безопасности», «проверь на уязвимости». НЕ активный пентест→агент security-engineer (режим PENTEST).
skill-auditЗаглушка: проверка чужого скилла/плагина до установки переехала в skill-manager, режим «Аудит». Сам не вызывается, держит старые ссылки живыми.
skill-managerНавыки и плагины: найти, подобрать, проверить. Триггеры: «найди скилл», «какой навык подходит», «безопасно ли ставить», «установи скилл». НЕ: создать→skill-creator; своё→leak-scan.
threat-huntingThreat hunting: правила Sigma, detection engineering. Триггеры: «охота на угрозы», «sigma rules». НЕ свой код → security-audit.
/code-health:health-bugsBug detection and fixing workflow (inline orchestration)
/code-health:health-cleanupDead code detection and cleanup workflow (inline orchestration)
/code-health:health-depsDependency audit and update workflow (inline orchestration)
/code-health:health-reuseCode duplication detection and consolidation workflow (inline orchestration)
/code-health:health-securitySecurity vulnerability detection and remediation workflow (inline orchestration)
/code-health:security-scanSecurity-аудит проекта: секреты в коде, pip/npm audit, OWASP Top 10, конфигурация DEBUG/CORS. Триггеры: «аудит безопасности», «проверь на уязвимости».
bug-fixerUse proactively to systematically fix bugs from bug-hunter reports. Specialist for processing bug-hunting-report.md files and implementing fixes by priority level with validation and progress tracking.
bug-hunterUse proactively for comprehensive bug detection, code validation, dead code identification, and generating prioritized fix tasks. Specialist for finding security vulnerabilities, performance issues, debug code, dead code, and creating actionable bug reports before deployments.
dead-code-hunterUse proactively to detect and report unused code, commented blocks, debug artifacts, and unreachable code in the codebase. Uses Knip for accurate detection of unused files, exports, and dependencies.
dead-code-removerSpecialist for safely removing dead code after analysis. Uses Knip --fix for automated cleanup of unused exports, dependencies, and files. Use when dead-code-report.md needs cleanup.
dependency-auditorSpecialist for analyzing dependency health, detecting security vulnerabilities, and identifying outdated or unused packages. Uses Knip for accurate unused dependency detection.
dependency-updaterUse for safe dependency updates, security fixes, and cleanup. Handles one dependency at a time with validation and rollback.
pentest-engineerPenetration testing and security assessment - vulnerability discovery, exploit analysis
reuse-fixerUse proactively to consolidate duplicated code from reuse-hunter reports. Specialist for processing reuse-hunting-report.md files and implementing Single Source of Truth pattern with re-exports by priority level with validation and progress tracking.
reuse-hunterUse proactively for comprehensive code duplication detection, identifying duplicated types, interfaces, Zod schemas, constants, and utility functions that should be consolidated using Single Source of Truth pattern. Specialist for finding reusable code opportunities and generating prioritized consol
security-engineerSecurity review, vulnerability assessment, secure coding, compliance auditing
security-scannerUse proactively for comprehensive security vulnerability scanning including SQL injection, XSS, authentication issues, RLS policy validation, and hardcoded secrets detection. Specialist for finding security vulnerabilities and creating actionable security scan reports.
vulnerability-fixerUse proactively to systematically fix security vulnerabilities from security-scan-report.md files. Specialist for implementing security fixes by priority level with validation and progress tracking.
Phase-based dev framework: roadmaps, plans, execution, verification, debugging.
57 commands · 18 agents
Same content as video-media, fetched as a sparse git-subdir clone of this monorepo. Reference entry for the git-subdir source format - install either this or video-media, not both.
53 skills · 3 commands · 9 agents
Python/JS/TS dev, database design, API docs, build fix, git workflow, architecture agents.
17 skills · 16 commands · 10 agents
8-role production pipeline (brief to QC), generation (Runway), avatars (HeyGen/D-ID), edit, download, export, subtitles, transcripts.
31 skills · 3 commands · 9 agents
n8n, AWS, Telegram bots, Zoom, Pinecone, DeepL, Home Assistant, webhooks.
24 skills · 6 commands · 2 agents
Figma import/export, PDF/PNG/PPTX export, dev handoff, verify, perf & a11y audits.
20 skills · 1 command · 3 agents
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
1 command · 6 agents
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
Without good data, your agent gives generic advice. Keyword research, competitor research, backlinks, and site audits. All for $10/month.
12 skills · 1 MCP server
Connect Claude to Prowler Cloud through the Prowler MCP server. Reads providers, scans, findings, compliance results and resources for AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and the other providers listed at https://registry.prowler.com, and returns remediation guidance for failed checks. Writes are limited to Prowler Cloud itself: triggering scans, finding triage, mute rules and the mutelist, providers and integrations. Your cloud resources are not changed by the connector.
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.