Skip to content

aiskillstore/marketplace / skills/0xrdan/route

Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)

FileKindSize
SKILL.mdskill md2.5 KB
skill-report.jsonconfig20.9 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T14:13:55.180Z",
    "slug": "0xrdan-route",
    "source_url": "https://github.com/0xrdan/claude-router/tree/main/.claude-plugin/skills/route",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "53b568d09bb8d2bbe51cbe083732c6b86ed84befe3365cec2f94b107355674e0",
    "tree_hash": "0b08ffff72c855868bfda206aede608c8050d28b4b362e32db3d6f5429c7c2a3",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "route",
    "description": "Route a prompt to Haiku, Sonnet, or Opus through explicit manual model selection.",
    "summary": "Manual Claude model routing for prompts that need a chosen model.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xrdan",
    "license": "MIT",
    "tags": [
      "model-routing",
      "claude",
      "prompt-control",
      "subagents",
      "workflow"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ],
    "category": "productivity"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static findings were false positives caused by Markdown code fences, inline code labels, and usage examples. No executable code, network access, filesystem access, environment reads, prompt injection attempt, or data exfiltration intent was found in SKILL.md.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 15
          },
          {
            "file": "SKILL.md",
            "line_start": 15,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 19,
            "line_end": 19
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 51,
            "line_end": 51
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 62
          },
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 86
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 15,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 15,
        "line_end": 17,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 18,
        "snippet": "Where `<model>` is one of:"
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "- `haiku` or `fast` - Use Haiku for simple, quick tasks"
      },
      {
        "id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 19,
        "line_end": 19,
        "snippet": "- `sonnet` or `standard` - Use Sonnet for typical coding tasks"
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 20,
        "line_end": 20,
        "snippet": "- `opus` or `deep` - Use Opus for complex analysis"
      },
      {
        "id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 49,
        "line_end": 49,
        "snippet": "| `haiku` or `fast` | fast-executor | Haiku |"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "| `sonnet` or `standard` | standard-executor | Sonnet |"
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 51,
        "line_end": 51,
        "snippet": "| `opus` or `deep` | deep-executor | Opus |"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 58,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 62,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 62,
        "line_end": 64,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 68,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 70,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 77,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 86,
        "snippet": "```"
      },
      {
        "id": "blocker:SKILL.md:30:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 30,
        "line_end": 30,
        "snippet": "3. **Validate** - If no valid model is specified, show usage help"
      },
      {
        "id": "blocker:SKILL.md:43:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 43,
        "line_end": 43,
        "snippet": "The user said which model. Use that model. Period."
      },
      {
        "id": "blocker:SKILL.md:75:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 75,
        "snippet": "If the user doesn't provide a valid model, respond with:"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 13-15 are a Markdown code fence containing the /route usage pattern. They are documentation text, not Ruby or shell execution."
      },
      {
        "id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 15-17 close the Markdown usage block and introduce model options. This is documentation syntax, not executable command logic."
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 17 describes a placeholder argument in prose. It does not execute backticks or invoke an external command."
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 18 uses inline Markdown code for the haiku and fast aliases. No shell command or interpreter call is present."
      },
      {
        "id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 19 uses inline Markdown code for the sonnet and standard aliases. The text only documents accepted arguments."
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 20 uses inline Markdown code for the opus and deep aliases. It is descriptive text with no executable behavior."
      },
      {
        "id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 49 is a Markdown table row that documents aliases and executor names. Inline code formatting is not shell execution."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 50 is a Markdown table row for Sonnet routing. It contains no command execution primitive or dynamic input handling."
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 51 is a Markdown table row for Opus routing. The backticks are formatting around labels, not executable code."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 56-58 are a Markdown example of a slash command invocation. It is documentation for users, not code that the skill runs."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 58-62 close one Markdown example and introduce another. The fenced block syntax is documentation, not shell execution."
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 62-64 show a Markdown example of routing to Haiku. The skill file contains text instructions only and no executable script."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 64-68 close the Haiku example and introduce the Sonnet example. This is static Markdown content, not an external command."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 68-70 show a Markdown example of routing to Sonnet. The fenced text is not evaluated as Ruby or shell."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 70-77 are narrative example and error-handling documentation around a Markdown fence. No shell execution path is present."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Lines 77-86 are a fenced usage-help message. This is output text the assistant should show, not code to execute."
      },
      {
        "id": "blocker:SKILL.md:30:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 30 tells the assistant to show usage help when the model argument is invalid. It does not inspect the system or gather environment information."
      },
      {
        "id": "blocker:SKILL.md:43:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 43 reinforces honoring the user-selected model. It is routing behavior, not reconnaissance or host inspection."
      },
      {
        "id": "blocker:SKILL.md:75:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 75 introduces an error message for invalid input. It does not request system data, secrets, files, or environment details."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 87,
    "audit_model": "codex",
    "audited_at": "2026-07-04T14:13:55.180Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Route Prompts to a Chosen Claude Model",
    "value_statement": "Automatic model selection can pick a different model than the user intended. This skill lets users explicitly route a prompt to Haiku, Sonnet, or Opus.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "model routing",
      "manual model selection",
      "Haiku",
      "Sonnet",
      "Opus",
      "AI skill marketplace",
      "prompt routing"
    ],
    "actual_capabilities": [
      "Parses the first argument as a requested model alias.",
      "Supports haiku, fast, sonnet, standard, opus, and deep aliases.",
      "Routes requests to fast, standard, or deep executor subagents.",
      "Preserves the remaining user query for the selected executor.",
      "Shows usage help when the model alias is missing or invalid.",
      "Labels the response with the model used."
    ],
    "limitations": [
      "It does not choose a model automatically.",
      "It depends on matching executor subagents being available.",
      "It only supports Haiku, Sonnet, and Opus model classes.",
      "It does not estimate cost, latency, or policy impact."
    ],
    "use_cases": [
      {
        "title": "Control Model Cost",
        "description": "Route simple requests to Haiku when speed and cost matter more than deep reasoning.",
        "target_user": "Individual developers"
      },
      {
        "title": "Standardize Team Workflows",
        "description": "Send normal coding tasks to Sonnet so team members use a consistent default model.",
        "target_user": "Engineering teams"
      },
      {
        "title": "Force Deep Review",
        "description": "Route architecture, security, or design reviews to Opus when the task needs deeper analysis.",
        "target_user": "Technical leads"
      }
    ],
    "prompt_templates": [
      {
        "title": "Route a Quick Summary",
        "scenario": "Beginner request for a fast answer.",
        "prompt": "/route haiku Summarize this issue in three direct bullets."
      },
      {
        "title": "Route a Coding Task",
        "scenario": "Routine development help with the standard model.",
        "prompt": "/route sonnet Review this component and suggest focused improvements."
      },
      {
        "title": "Route a Deep Analysis",
        "scenario": "Complex reasoning where the user wants the strongest model.",
        "prompt": "/route opus Analyze this authentication flow for design risks and missing checks."
      },
      {
        "title": "Use Alias-Based Routing",
        "scenario": "Advanced workflow using shorter model aliases.",
        "prompt": "/route deep Compare these migration options and recommend a rollout plan."
      }
    ],
    "output_examples": [
      {
        "input": "A user requests Opus for an authentication design review.",
        "output": "The assistant routes the request to the deep executor and labels the response as Opus."
      },
      {
        "input": "A user requests Haiku for a short summary task.",
        "output": "The assistant routes the request to the fast executor and labels the response as Haiku."
      },
      {
        "input": "A user enters an unsupported model name.",
        "output": "The assistant returns concise usage help with the supported model aliases."
      }
    ],
    "best_practices": [
      "Choose Haiku for simple tasks that need fast responses.",
      "Choose Sonnet for routine coding, documentation, and review work.",
      "Choose Opus for complex analysis where accuracy matters more than cost."
    ],
    "anti_patterns": [
      "Do not expect the skill to classify task complexity automatically.",
      "Do not use the most capable model for every short request.",
      "Do not use routing instructions to bypass platform safety requirements."
    ],
    "faq": [
      {
        "question": "Does this skill choose the model automatically?",
        "answer": "No. The user must provide a supported model alias as the first argument."
      },
      {
        "question": "Which model aliases are supported?",
        "answer": "It supports haiku, fast, sonnet, standard, opus, and deep."
      },
      {
        "question": "What happens after a valid model is selected?",
        "answer": "The skill routes the remaining query to the matching executor subagent."
      },
      {
        "question": "Can it route non-coding tasks?",
        "answer": "Yes. The routing logic is based on the requested model, not the task topic."
      },
      {
        "question": "Does it reduce token cost by itself?",
        "answer": "No. It only routes to the selected model. Cost depends on the chosen model and request size."
      },
      {
        "question": "What should I do when the alias is invalid?",
        "answer": "Use one of the documented aliases, then place the full query after the alias."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 87
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall