coreyhaines31/makerskills / skills/castmate
castmate
FlaggedWhen you want to pull in the right AI model for the right job: hand a task to another agent CLI (Codex, Claude, Gemini, Grok, Amp, OpenCode, Cursor, Kiro, Antigravity), or send one prompt to several at once for independent opinions, then synthesize. Delegate mode gives one castmate the job, optionally with write access ('have codex write the migration'). Fan-out mode runs read-only reviews in parallel. Rounds mode lets castmates build on and challenge each other's findings. Calls the official CLIs you already have installed and logged in (Gemini CLI needs an API key on personal accounts); no MCP. Triggers on '/castmate,' 'ask codex,' 'have gemini do this,' 'get a second opinion,' 'what would other models say,' 'fan this out,' 'cross-check this with another model,' 'delegate this to codex.' Advisor personas for founder questions go to maker-council. Personal models, casting rules, and run outputs live in ~/.config/makerskills/castmate/.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.7 KB |
| references/amp-readonly-settings.json | config | 229 B |
| references/casting.md | markdown | 2.6 KB |
| references/cli-setup.md | markdown | 11.3 KB |
| references/gemini-readonly-policy.toml | config | 857 B |
| references/presets/README.md | markdown | 757 B |
| references/presets/bughunt.md | markdown | 1.6 KB |
| references/presets/contracts.md | markdown | 1.1 KB |
| references/presets/hotspots.md | markdown | 1.7 KB |
| references/presets/invariants.md | markdown | 1.5 KB |
| references/presets/regression.md | markdown | 1.1 KB |
| references/presets/security.md | markdown | 1.5 KB |
| references/prompt-template.md | markdown | 3.1 KB |
| references/tools.json | config | 9.1 KB |
| scripts/castmate.pyexecutable | script | 21.1 KB |
| scripts/test_castmate.py | script | 11.7 KB |
references/tools.json
View on GitHub{
"tools": {
"claude": {
"name": "Claude Code",
"binary": "claude",
"install": "https://docs.anthropic.com/en/docs/claude-code",
"verified": true,
"args": [
"-p",
"--output-format",
"text"
],
"prompt": "stdin",
"model": [
"--model",
"{model}"
],
"effort": [
"--effort",
"{effort}"
],
"readOnly": {
"level": "enforced",
"args": [
"--tools",
"Read,Glob,Grep,WebFetch,WebSearch",
"--allowedTools",
"Read,Glob,Grep,WebFetch,WebSearch",
"--strict-mcp-config",
"--safe-mode",
"--setting-sources",
"user",
"--permission-prompts",
"none",
"--no-session-persistence"
]
},
"write": {
"args": [
"--permission-mode",
"acceptEdits"
]
},
"setup": "claude-code"
},
"codex": {
"name": "OpenAI Codex",
"binary": "codex",
"install": "https://github.com/openai/codex",
"verified": true,
"args": [
"exec",
"--skip-git-repo-check",
"-o",
"{last_message}"
],
"argsAfter": [
"-"
],
"prompt": "stdin",
"output": "last_message",
"model": [
"-m",
"{model}"
],
"effort": [
"-c",
"model_reasoning_effort={effort}"
],
"readOnly": {
"level": "enforced",
"args": [
"--sandbox",
"read-only",
"--ignore-user-config",
"-c",
"features.apps=false"
]
},
"write": {
"args": [
"--sandbox",
"workspace-write"
]
},
"setup": "codex"
},
"gemini": {
"name": "Gemini CLI",
"binary": "gemini",
"install": "https://github.com/google-gemini/gemini-cli",
"verified": true,
"args": [
"-p",
"",
"--output-format",
"text",
"--skip-trust"
],
"prompt": "stdin",
"promptSuffix": "\n\nIMPORTANT: Do not narrate your tool usage, internal planning, or chain of thought. Start your response directly with your analysis.",
"model": [
"-m",
"{model}"
],
"readOnly": {
"level": "enforced",
"args": [
"--approval-mode",
"plan",
"--admin-policy",
"{refs}/gemini-readonly-policy.toml",
"--allowed-mcp-server-names",
"castmate-none"
]
},
"write": {
"args": [
"--approval-mode",
"auto_edit"
]
},
"setup": "gemini-cli"
},
"amp": {
"name": "Amp CLI",
"binary": "amp",
"install": "https://ampcode.com",
"verified": false,
"args": [
"-x"
],
"prompt": "stdin",
"model": [
"-m",
"{model}"
],
"readOnly": {
"level": "best-effort",
"args": [
"--settings-file",
"{refs}/amp-readonly-settings.json"
]
},
"write": {
"args": [
"--dangerously-allow-all"
]
},
"setup": "other-clis"
},
"opencode": {
"name": "OpenCode",
"binary": "opencode",
"install": "https://opencode.ai/docs/",
"verified": false,
"args": [
"run",
"--archived"
],
"argsAfter": [
"{prompt}"
],
"prompt": "arg",
"model": [
"--model",
"{model}"
],
"readOnly": {
"level": "best-effort",
"args": [
"--agent",
"plan"
],
"env": {
"OPENCODE_PERMISSION": "{\"*\":\"deny\",\"bash\":\"deny\",\"edit\":\"deny\",\"read\":{\"*\":\"allow\",\"*.env\":\"deny\",\"*.env.*\":\"deny\",\"*.env.example\":\"allow\"},\"glob\":\"allow\",\"grep\":\"allow\",\"list\":\"allow\",\"webfetch\":\"allow\",\"websearch\":\"allow\",\"codesearch\":\"allow\",\"lsp\":\"allow\"}"
}
},
"write": {
"args": [
"--auto"
]
},
"setup": "other-clis"
},
"cursor": {
"name": "Cursor Agent",
"binary": "cursor-agent",
"install": "https://cursor.com/cli",
"verified": false,
"args": [
"-p",
"--output-format",
"text"
],
"argsAfter": [
"{prompt}"
],
"prompt": "arg",
"model": [
"--model",
"{model}"
],
"readOnly": {
"level": "best-effort",
"args": [
"--mode",
"ask"
]
},
"write": {
"args": [
"--force"
]
},
"setup": "other-clis"
},
"kiro": {
"name": "Kiro CLI",
"binary": "kiro-cli",
"install": "https://kiro.dev/docs/cli/",
"verified": false,
"args": [
"chat",
"--no-interactive",
"--wrap",
"never"
],
"prompt": "stdin",
"model": [
"--model",
"{model}"
],
"readOnly": {
"level": "best-effort",
"args": [
"--trust-tools",
"fs_read,fs_list,fs_search,web_search,web_fetch"
]
},
"write": {
"args": [
"--trust-all-tools"
]
},
"setup": "other-clis"
},
"antigravity": {
"name": "Antigravity CLI",
"binary": "agy",
"install": "https://antigravity.google/docs/cli/install",
"verified": true,
"args": [
"--add-dir",
"{cwd}",
"--print-timeout",
"{timeout_plus}s"
],
"argsAfter": [
"-p",
"{prompt}"
],
"prompt": "arg",
"model": [
"--model",
"{model}"
],
"readOnly": {
"level": "best-effort",
"args": [
"--mode",
"plan",
"--sandbox"
]
},
"write": {
"args": [
"--mode",
"accept-edits"
]
},
"effort": [
"--effort",
"{effort}"
],
"promptSuffix": "\n\nIMPORTANT: Shell commands are unavailable in this session and any attempt ends the run with no answer. Use only file read and search tools. If the task needs a command, say so in your answer instead of running it.",
"setup": "antigravity"
}
},
"castmates": {
"fable": {
"tool": "claude",
"model": "fable",
"note": "Claude Fable 5"
},
"fable-high": {
"tool": "claude",
"model": "fable",
"effort": "high",
"note": "Claude Fable 5, high effort"
},
"opus": {
"tool": "claude",
"model": "opus",
"note": "Claude Opus, latest"
},
"sonnet": {
"tool": "claude",
"model": "sonnet",
"note": "Claude Sonnet, latest"
},
"haiku": {
"tool": "claude",
"model": "haiku",
"note": "Claude Haiku, latest (fast, cheap)"
},
"codex": {
"tool": "codex",
"note": "Codex CLI default model"
},
"codex-sol-high": {
"tool": "codex",
"model": "gpt-5.6-sol",
"effort": "high",
"note": "GPT-5.6 Sol, high reasoning"
},
"codex-sol-xhigh": {
"tool": "codex",
"model": "gpt-5.6-sol",
"effort": "xhigh",
"note": "GPT-5.6 Sol, xhigh reasoning"
},
"codex-sol-medium": {
"tool": "codex",
"model": "gpt-5.6-sol",
"effort": "medium",
"note": "GPT-5.6 Sol, medium reasoning"
},
"codex-terra": {
"tool": "codex",
"model": "gpt-5.6-terra",
"note": "GPT-5.6 Terra"
},
"codex-luna": {
"tool": "codex",
"model": "gpt-5.6-luna",
"note": "GPT-5.6 Luna (fast)"
},
"gemini-pro": {
"tool": "gemini",
"model": "gemini-3.1-pro-preview",
"note": "Gemini 3.1 Pro"
},
"gemini-flash": {
"tool": "gemini",
"model": "gemini-3-flash-preview",
"note": "Gemini 3 Flash"
},
"amp-smart": {
"tool": "amp",
"model": "smart",
"note": "Amp smart mode"
},
"opencode": {
"tool": "opencode",
"note": "OpenCode default model"
},
"grok": {
"tool": "opencode",
"model": "xai/grok-4.7",
"note": "Grok 4.7 via OpenCode (needs XAI_API_KEY)"
},
"cursor": {
"tool": "cursor",
"note": "Cursor Agent default model"
},
"kiro": {
"tool": "kiro",
"model": "auto",
"note": "Kiro auto model"
},
"antigravity": {
"tool": "antigravity",
"model": "gemini-3.8-flash-high",
"note": "Gemini 3.8 Flash (high) via Antigravity"
},
"gemini-argon": {
"tool": "gemini",
"model": "gemini-4-argon",
"note": "Gemini 4 Argon"
},
"codex-research": {
"tool": "codex",
"model": "gpt-5.6-sol",
"effort": "high",
"extraArgs": [
"-c",
"web_search=live"
],
"note": "GPT-5.6 Sol with live web search"
}
},
"groups": {
"review": [
"fable-high",
"codex-sol-high"
],
"wide": [
"fable-high",
"codex-sol-high",
"gemini-argon"
]
},
"defaults": {
"timeout": 540,
"maxParallel": 4
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |