codex

My Agents

Curated agent profiles for development, review, research, and orchestration.

0 on GitHubby VeigaPunkv0.2.0MITupdated 19 days agoDeveloper

Plugin myagents in VeigaPunk/ds4cc-marketplace. Commands read from the repo's manifest — 19 days ago.

What it installs

Skills (3)

  • godspeed

    Use on every prompt, including nested and delegated prompts, without waiting for a keyword. Explicit "godspeed" and "--with godspeed" invocation remains supported.

  • myagents-docs

    Discover and launch user-defined agent profiles from the myagents catalog on Grok Build or Codex.

  • wwkd

    What Would Karpathy Do — a planning and implementation posture distilled from Karpathy's public body of work (the Recipe, builder philosophy, vibe coding, context engineering). Activate when the user wants to turn an approved spec into an implementation plan, or asks "plan this", "break this down",

Subagents (16)

  • the-architect

    Architecture specialist for system boundaries, dependency direction, ADRs, integration seams, and migration shape. Produces actionable structural decisions without duplicating planning, critique, or code review.

  • the-bootstrapper

    Roster bootstrapper — scans installed agent rosters on command and assigns delegation lanes with live OAuth/token-plan model routing via the bootstrapper script. Use when asked to inventory available subagents, refresh delegations, audit which models routes resolve to, or bootstrap an orchestration

  • the-connector

    Cross-axis pattern matcher. Sees the whole table, calls out unusual connections and second-order effects. Breadth over depth.

  • the-critic

    Approach-level adversarial reviewer. Challenges design decisions, architectural assumptions, and strategy choices. Distinct from reviewer (code bugs) and sentinel (security).

  • the-distiller

    Deduplicates N parallel findings, flags contradictions, assigns confidence scores. Text synthesis with optional tool verification. Sits between workers and the-judge.

  • the-executor

    Writes code, runs tests, returns results. Stateless by default — scoped to one subtask. Delegates to Codex Spark for implementation review.

  • the-judge

    Orchestrator and arbiter. Names axes, dispatches specialists, applies Pareto filter, drafts implementation. Top of the stack — spawns others, never spawned.

  • the-labrat

    Expendable single-shot probe. Tests one hypothesis cheap and fast. State nuked on despawn. Defaults to Codex Spark.

  • the-mutation-tester

    Adversarial test suite validator. Generates code mutations, runs them against tests, reports which mutations survive — exposing test suite gaps.

  • the-planner

    Owns pre-execution planning and Phase 0 data-walk. Produces the first-mile wwkd plan artifact for executors.

  • the-revenger

    Reverse engineering specialist. Reads systems, APIs, codebases, and protocols — maps behavior, infers intent, reproduces functionality. Godspeed is always active.

  • the-reviewer

    Surgical code reviewer. Finds the bug that ships to prod. Delegates to Codex for deep reviews.

  • the-scout

    Research lens. Finds what exists outside the repo — libraries, docs, prior art, and release notes. Defaults to Codex Spark delegation.

  • the-scribe

    Writes Carpaccio milestone reports and executes git commits. One report + one gate + one commit per milestone — the auditable-trail anchor.

  • the-sentinel

    Security auditor. Attacker-minded — hunts vulnerabilities, injection vectors, insecure configs, and privilege escalation paths. Full tool access for scanning and remediation.

  • the-simplifier

    YAGNI enforcer. Finds what to delete. If removing it passes all tests, it was dead. Asks "would this still be worthwhile if the task disappeared?

View source on GitHub ds4cc.com

More from VeigaPunk/ds4cc-marketplace

All 20 plugins →

Drive Grok-only web UI features through agent-browser and an authenticated CDP profile.

1 skill · 16 agents

0

Read-only guidance for discovering reviewed DS4CC plugins and installing them with Grok Build, Codex, Kimi Code, and OpenCode bootstrap after source review.

1 skill · 15 agents

0

Set Grok Bot as a Vegapunk round table. Say 'set grok bot for me' in your preferred CLI.

1 skill · 2 commands · 7 agents

0

Empirical network configuration audits with adversarial validation.

1 skill · 1 agent

0

aaron CLI tool for Codex hosts — invoke via Bash, not as an agent.

1 skill

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain My Agents?

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.

claude & codex plugins20 plugins