Skip to content

oliverv/caro / .agents/skills/oma-orchestration

oma-orchestration

Unverified

Dispatch and supervise parallel specialist agents with durable task state. Use when automated multi-agent execution is requested.

FileKindSize
SKILL.mdskill md15.6 KB
config/cli-config.yamlconfig3.4 KB
resources/memory-schema.mdmarkdown6.7 KB
resources/subagent-prompt-template.mdmarkdown1.5 KB
scripts/parallel-run.shexecutablescript231 B
scripts/spawn-agent.shexecutablescript178 B
scripts/verify.shexecutablescript542 B
templates/backend-task.mdmarkdown634 B
templates/debug-task.mdmarkdown339 B
templates/frontend-task.mdmarkdown582 B
templates/mobile-task.mdmarkdown588 B
templates/qa-task.mdmarkdown441 B
templates/tasks-example.yamlconfig418 B

config/cli-config.yaml

View on GitHub
# SubAgent CLI Configuration
# Select your preferred CLI vendor for sub-agent execution

# NO LONGER READ. Set `default_cli:` in .agents/oma-config.yaml instead — this
# file is overwritten by `oma update`, and migration 022 moves a non-default
# value across for you. For per-agent CLI mapping, see .agents/oma-config.yaml.
active_vendor: claude

# Vendor configurations
vendors:
  claude:
    command: claude
    prompt_flag: "-p"
    output_format_flag: "--output-format"
    output_format: "json"
    auto_approve_flag: "--dangerously-skip-permissions"
    model_flag: "--model"
    default_model: "sonnet"
    # JSON output parsing
    response_jq: ".result"
    isolation_method: "flags"

  codex:
    command: codex
    subcommand: "exec"
    prompt_flag: "none"
    output_format_flag: "--json"
    auto_approve_flag: "--full-auto"
    model_flag: "-m"
    default_model: "gpt-5.5"
    response_jq: ".response"
    isolation_method: "directory"

  qwen:
    command: qwen
    prompt_flag: "-p"
    output_format_flag: "--output-format"
    output_format: "json"
    auto_approve_flag: "--yolo"
    model_flag: "-m"
    default_model: "qwen3.6-plus"
    response_jq: ".output"
    isolation_method: "directory"

  # Antigravity (agy) headless print mode: `agy -p "<prompt>"`.
  # Models: run `agy models`. `--model` accepts ONLY those display names —
  # a slug like `gemini-3.1-pro` makes agy exit with `Error: invalid --model`
  # before running the prompt. The parenthesised tier is agy's effort dial.
  # agy 1.0 had no --model / --add-dir / --print-timeout; oma probes
  # `agy --help` once and drops whichever flags the installed binary lacks.
  antigravity:
    command: agy
    prompt_flag: "-p"
    auto_approve_flag: "--dangerously-skip-permissions"
    model_flag: "--model"
    default_model: "Gemini 3.1 Pro (High)"
    isolation_method: "directory"

  # Cursor Agent headless CLI: `cursor agent -p …` (--print). Prompt is positional.
  # Models: run `cursor agent models` (legacy fallback: `cursor agent --list-models`).
  # `auto` lets Cursor route to an available model (quota-friendly); pin to a specific
  # id (e.g. composer-2.5, composer-2.5-fast) for reproducibility.
  cursor:
    command: cursor
    prompt_flag: none
    output_format_flag: "--output-format"
    output_format: "json"
    auto_approve_flag: "--yolo"
    model_flag: "--model"
    default_model: "auto"
    isolation_method: "directory"

  # Kiro CLI headless: `kiro-cli chat --no-interactive --trust-all-tools [--model …] "<prompt>"`.
  # Models: AWS Bedrock IDs (e.g. anthropic.claude-sonnet-4-5-20251001-v1:0).
  # Use "auto" to let Kiro select the model based on its own configuration.
  kiro:
    command: kiro-cli
    prompt_flag: none
    auto_approve_flag: "--trust-all-tools"
    model_flag: "--model"
    default_model: "auto"
    isolation_method: "directory"

  # pi headless print mode: `pi [--model …] -p "<prompt>"`.
  # Model accepts any pi model pattern/alias, including thinking suffixes.
  pi:
    command: pi
    prompt_flag: "-p"
    model_flag: "--model"
    default_model: "sonnet:high"
    isolation_method: "directory"

# SubAgent execution settings
execution:
  # Directory for subagent results
  results_dir: ".agents/results"
  # Timeout in seconds (0 = no timeout)
  timeout: 600
  # Log level: debug, info, warn, error
  log_level: info
  # Keep intermediate files for debugging
  keep_temp_files: false
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall