131 tagged openai, measured the same way as everything else here.
Browse within: litellm 21self-hosted 21HuggingFace 17LangChain 15artificial-intelligence 15langgraph 14ollama 14ai-engineering 13fal 12gemini 12maintainer-tools 12awesome-list 10chatgpt 9claudecode 9
solygambas/python-openai-projects
Agent Claude Code
Use this agent to perform a focused security audit of authentication-related code (NextAuth v5 credentials + GitHub, email verification, password reset, and profile update flows). It reports only real, validated issues and writes results to docs/audit-results/AUTHSECURITYREVIEW.md.
solygambas/python-openai-projects
Agent Claude Code
Use this agent when you need to audit a Next.js codebase for security vulnerabilities, performance bottlenecks, code quality issues, or opportunities to refactor code into smaller components. This agent focuses on actual implemented code and does not flag missing features or unimplemented…
solygambas/python-openai-projects
Agent Claude Code
Use this agent when you need to scan a codebase for repeated code patterns, duplicated logic, and inline helpers that can be extracted into reusable utility functions. This agent focuses specifically on DRY violations and refactoring opportunities, not security or performance. Examples: Context: User wants to find…
Agent
Branch a conversation at a completed-run boundary — persistent forks for new threads, ephemeral one-shot probes, and the HITL binding rules that keep them safe.
Agent
How CubePi maximises prompt cache hit rates — append-only message storage, automatic cache breakpoints, and how to avoid breaking the cache.
Agent
Register tools, execute them in parallel or sequentially, and handle results with Pydantic validation in CubePi.
Agent
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with specific files to create or modify, component designs, data flows, and a build sequence.
Agent
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development.
Agent
Scope: hypervisor.py · spawnagent.py · agentcontext.py · attestation.py · agentregistry.py · builtinagents.py. A closed subsystem: these modules reference each other's types and are meaningless apart.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
Agent
Reviews a supplied diff for introduced, practically exploitable security vulnerabilities. Use only when dispatched by the code-review skill.
Agent
Reviews a supplied diff for introduced, concrete design and maintainability hazards. Use only when dispatched by the code-review skill.
Agent
Agent "orchestrator" from Kbediako/codex-termux-pocket, covering user updates spec, reviews and general guidelines.
Agent
Journaling assistant that helps the user reflect, capture entries, and surface patterns over time.
Agent
UI design specialist for web, mobile, and desktop apps; advises on layout, hierarchy, and interaction patterns.
Agent
Writing assistant for drafting, refining, fixing grammar, and translating text.
Agent
Backend analysis, architecture review, and implementation guidance.
Agent
Coordinates multi-agent AI reasoning tasks.
Agent
Requirements analysis, tracing, and validation.
ASMN-96/ai-agents-skills-toolkit
Agent
Reviews database schema, Postgres/ORM access boundaries, Supabase/RLS policies when present, migrations, tenant isolation, data exposure, destructive-operation risk, and rollback safety.
ASMN-96/ai-agents-skills-toolkit
Agent
Read-only advisory project agent for release readiness coordination. It evaluates whether a branch, PR, source-refresh pass, or toolkit release has enough observed evidence for a merge/no-merge posture, then routes the final readiness posture through pr-release-gate.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: