Agent
Fully autonomous unattended agent.
267 tagged coding agents, measured the same way as everything else here.
Browse within: git-worktree 45kanban 45vibe-coding 45agent-memory 40codex-skills 30copilot-skills 30agent-config 20ai-workflow 20pi 20repotrace 20codebase 19ai-agents-framework 18code-visualization 18knowledge-graph 18
Agent
Fully autonomous unattended agent.
Agent
Always use for focused isolated code executor.
Agent
Always use for autonomous verified task solver.
Agent
PACEflow artifact 操作专员。处理索引文件(task / walkthrough / findings / corrections.md)和 changes/ 子目录详情文件的 CRUD。 详细规范在 ${CLAUDEPLUGINROOT}/agent-references/artifact-writer-spec.md 与 ${CLAUDEPLUGINROOT}/agent-references/instructions/。.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues and PRDs for this repo live as markdown files in .scratch/.
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
FlyFission/nuclear-grade-context-engineering
Agent
PROVE Verdict stage. Use to make the ship / block / defer / ship-with-named-risk decision on the presented evidence — read-only and context-separated from the runner, but still coupled through the orchestrator and possibly model/resources. Do not use to build, gather new evidence, or write code.
FlyFission/nuclear-grade-context-engineering
Agent
PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — with no Edit/Write authority over product code, so it cannot directly patch code to pass its own evidence. Do not use to build, plan, or decide ship/block.
FlyFission/nuclear-grade-context-engineering
Agent
PROVE Plan stage. Use to turn a request into an approved plan — question, discover, specify, plan — writing only to the change packet, never product code. Dispatch first, before any building. Do not use to edit code, run commands, or decide ship/block.
Agent
You are building with the Odds API: a data-access interface for odds, betting, sports, racing, events, results, bookmakers, and market data.
Agent
Follow agents/AGENTS.md. Prefer the SDKs or MCP tools for data access. Build the user's requested product instead of copying repo examples by default; examples are optional references. For realtime products, use oddsapi.getstreaminginfo and oddsapi.getstreamconnection, then generate code that connects directly to raw…
Agent
Build against openapi.yaml and the SDKs in this repo. Use API-key auth first. Design the requested app or workflow rather than copying bundled examples; examples are optional references. Prefer snapshots for one-off answers; use oddsapi.getstreaminginfo and oddsapi.getstreamconnection before realtime code, then…
Agent
Brand consistency validator. This agent audits content against the brand profile to ensure every piece of content aligns with the defined identity, voice, and visual standards. It is the quality gate before content ships.
Agent
Content format transformer. This agent takes a single piece of content and adapts it into different formats for different platforms. It maintains brand consistency while respecting each platform's unique norms and constraints.
Agent
Long-form content writer. This agent produces blog posts, articles, deep dives, tutorials, case studies, and other substantial written content. Every word must earn its place.
Agent Claude Code
Coordinates autonomous Claude Code agents via the octomux CLI. Creates tasks, monitors progress, manages agent lifecycles.
Agent Claude Code
Reads a codebase and produces a concrete implementation plan from a feature request, bug report, or Jira ticket.
Agent Claude Code
Comprehensive code reviewer. Use when asked to review a PR, diff, branch, or specific files/folders. Spawns 7 specialized sub-reviewers in parallel, then synthesizes findings into a prioritized verdict.
Agent
Reviews code for quality and best practices.
Agent
Specializes in debugging and root cause analysis.
Agent
A test agent for E2E testing.
Agent
Agent "claude-code" from thixpin/pitway, covering claude code, what gets installed, the driver never touches state directly and shared content, not a fork.
Agent
Agent "codex" from thixpin/pitway, covering codex, what gets installed and same gates, same boundaries.