Agora Runner — Development agent for Claude Code
Executes exactly one agora session step (start, one round, or finish) via the skill scripts and returns only a verdict summary.
How to install Agora Runner
Installs to ~/.claude/agents/baekenough-oh-my-customcode-agora-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/baekenough/oh-my-customcode/HEAD/.claude/agents/agora-runner.md -o ~/.claude/agents/baekenough-oh-my-customcode-agora-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Agora Runner does
name: agora-runner description: Executes exactly one agora session step (start, one round, or finish) via the skill scripts and returns only a verdict summary. Never returns reviewer text, vendor attribution or sealed paths. model: claude-sonnet-5 tools: [Bash, Read, Write, Glob] skills: [agora]
역할
`agora` 스킬에서 **파일을 쓰는 진입점 전부**를 전담합니다 — `--start`, `--round`, `--set-stop`, `--report` 넷입니다. 오케스트레이터는 파일을 쓰지 않는 `--gate`만 직접 실행합니다(R010).
**위임 1건 = 아래 단계 하나**이며, 여러 단계를 한 번에 처리하지 않습니다 (R
Alternatives in Development
- Slack Archaeologist — Deep reconstruction of Slack conversations 4.6k ★
- Lex Legal — Use this agent when dealing with legal and compliance activities 523 ★
- Agora Nietzsche — Agora member 168 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kss Runner
KSS runner — sonnet, low effort. Runs exactly the command it is given (tests, lint, tsc, build) and returns on
Track Builder
경기장 노면·차선·도로 마킹·포트홀·배리어·헬리패드를 Blender Python으로 제작하는 전문가. 10_ground.py, 20_markings.py, 30_hazards.py를 산출한다. 아스
Exec E2e Runner
An e2e runner of the stage-4 round — executes EVERY case of ONE scope against the staging environment with rea
Ingest Runner
Executes the fast and lean ingest pipeline (skills/ingest/SKILL.md) for exactly one source — Python-first Raw
Framework Runner
Execute one /mos: methodology per invocation in an isolated context. Files the artifact and returns a structur
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Related Skills
Claude Token Lens
See exactly what's burning your Claude Code quota — live. Per-tool, per-agent, per-skill, per-MCP attribution.
Mythos Harness
A finish-first agent loop for Claude Opus 4.7 — plans, executes, verifies, and ships.
Claude n8n Bridge
Self-hosted n8n in Docker wired to Claude Code: n8n owns schedules and webhooks, a host-side runner executes o