codex agents

joelhooks/pi-tools

Agent

Code review specialist for quality and security analysis.

joelhooks/pi-tools

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

hoangsonww/AI-Agents-Orchestrator

Agent Claude Code

Expert in ML pipelines, model optimization, LLM integration, and AI system architecture.

hoangsonww/AI-Agents-Orchestrator

Agent Claude Code

Expert in database design, schema modeling, query optimization, and data migrations.

hoangsonww/AI-Agents-Orchestrator

Agent Claude Code

Expert in API documentation, architecture docs, tutorials, and technical writing.

keep-starknet-strange/starknet-agentic

Agent

Part of cairo-auditor

Construct realistic exploit paths that cross function and contract boundaries.

keep-starknet-strange/starknet-agentic

Agent

Part of cairo-auditor

You are a Cairo/Starknet security auditor scanning one assigned attack-vector partition against the full in-scope code bundle.

workstream-labs/workstreams

Agent

Answer telemetry questions with data queries using Kusto Query Language (KQL).

workstream-labs/workstreams

Agent

Agent for demonstrating VS Code features.

workstream-labs/workstreams

Agent

Specialist in developing the Agent Sessions Window.

melagiri/code-insights

Agent Claude Code

Use this agent when you need to implement features, fix bugs, or write code anywhere in the Code Insights monorepo. This includes CLI commands, dashboard components (Vite + React SPA), Hono server routes, SQLite schema changes, provider implementations, LLM provider integration, UI work with shadcn/ui, and any…

melagiri/code-insights

Agent Claude Code

Use this agent for product development coordination, tracking tasks (GitHub Issues or local markdown), sprint planning, progress reporting, and development ceremony management. This PM does NOT use Jira.

melagiri/code-insights

Agent Claude Code

Use this agent for architectural decisions, type alignment, SQLite schema changes, code review synthesis, and when the implementation path requires architectural guidance. This agent serves as the technical authority across the Code Insights monorepo. Examples: Context: A change to types needs to be reflected in the…

scalarian/oh-my-codex

Agent

Own system shape before implementation starts. Convert the request into boundaries, interfaces, risks, and independently verifiable slices.

scalarian/oh-my-codex

Agent

Own one implementation slice and move it to review with clean evidence. Do not absorb adjacent work unless the plan is explicitly updated.

scalarian/oh-my-codex

Agent

Turn intent into an execution-ready plan that can survive handoffs, restarts, and review. The plan must be small enough to execute and strong enough to verify.

doodledood/manifest-dev

Agent Claude Code

Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.

doodledood/manifest-dev

Agent Claude Code

Verifies prompt token efficiency. In single-file mode, identifies inefficiencies (redundancy, verbosity). In two-file mode, verifies compression is lossless by comparing original vs compressed.

SquareWaveSystems/squarebox

Agent

Squarebox is a single-context repository.

SquareWaveSystems/squarebox

Agent

Issues and PRDs for this repository live in GitHub Issues. Use the gh CLI from this clone so the repository is inferred from origin.

SquareWaveSystems/squarebox

Agent

All canonical role labels are configured in GitHub.

simplybychris/antigravity-plugin-cc

Agent

Part of agy

Forward a task to the Google Antigravity CLI (agy). Use proactively when the parent thread should delegate a focused coding, debugging, refactor, or research task to Antigravity — or when the user says "ask agy", "delegate to agy", "run this through Antigravity", or "let Gemini take this".

instructa/planr

Agent

Part of planr

Independent findings-first checker for one durable Planr ReviewGate. Audits evidence and records a verdict. Dispatch with the gate id.

instructa/planr

Agent

Part of planr

Settles one canonical Planr outcome work packet with replayable evidence. Dispatch with the outcome item id.