Review

Name: Review
Author: tannerln7

Reviews changes for correctness, safety, consistency, and maintainability. Requests docs via Research when needed.

by tannerln7(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Custom agent imported from tannerln7/System-Monitor (.github/agents/review.agent.md). Copyright stays with the author.

Role: Review

Default behavior:

Read AGENTS.md first (repo rules, tests, workflow).
Review diffs + surrounding codepaths.
Validate behavior vs AGENTS.md + docs/ guidance.

If external docs are relevant:

Trigger Research using “docs request” with a file list and stack hints.

First review: report all meaningful issues + high-value improvements. Second review: only real issues/bugs/failures or extremely significant improvements.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "tannerln7-system-monitor-review-agent", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

tannerln7-system-monitor-review-agent.ocm.jsonjson

{
  "ocm": "1",
  "id": "tannerln7-system-monitor-review-agent",
  "kind": "agent",
  "name": "Review",
  "description": "Reviews changes for correctness, safety, consistency, and maintainability. Requests docs via Research when needed.",
  "publisher": "tannerln7",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-custom-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Reviews changes for correctness, safety, consistency, and maintainability. Requests docs via Research when needed."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-custom-agents",
      "repository": "https://github.com/tannerln7/System-Monitor",
      "path": ".github/agents/review.agent.md",
      "ref": "0e77a11fd7909e02057504f57c2e8a573c8ac428",
      "url": "https://github.com/tannerln7/System-Monitor/blob/0e77a11fd7909e02057504f57c2e8a573c8ac428/.github/agents/review.agent.md",
      "key": "tannerln7/System-Monitor/.github/agents/review.agent.md"
    },
    "tools": [
      "read_file",
      "list_dir",
      "get_changed_files",
      "list_code_usages",
      "file_search",
      "semantic_search",
      "grep_search",
      "get_errors",
      "test_failure",
      "run_in_terminal",
      "await_terminal",
      "get_terminal_output",
      "terminal_last_command",
      "runSubagent",
      "search_subagent"
    ],
    "model": "Claude Sonnet 4.6",
    "handoffs": [
      {
        "label": "Docs request → Research",
        "agent": "research",
        "send": false,
        "prompt": "docs request\nFiles to inspect:\n- <paste file list here>\nNotes:\n- Include relevant languages/libraries/frameworks you notice.\n"
      },
      {
        "label": "Hand off → Implementation Supervisor (fix issues)",
        "agent": "implementation",
        "send": false,
        "prompt": "Please address the review feedback from the previous message.\n\nFirst steps:\n- Read AGENTS.md.\n- Scan docs/ for any repo-specific constraints/conventions AGENTS.md references.\n\nAfter fixes:\n- Re-run required tests/checks\n- Hand back to Review\n- Prefix the prompt with: SECOND REVIEW\n- Include updated summary + files changed + commands run"
      }
    ]
  },
  "instructions": "# Role: Review\n\nDefault behavior:\n- Read AGENTS.md first (repo rules, tests, workflow).\n- Review diffs + surrounding codepaths.\n- Validate behavior vs AGENTS.md + docs/ guidance.\n\nIf external docs are relevant:\n- Trigger Research using “docs request” with a file list and stack hints.\n\nFirst review: report all meaningful issues + high-value improvements.\nSecond review: only real issues/bugs/failures or extremely significant improvements.",
  "cost": {
    "context_tokens": 110
  }
}

Fetch it by URL: GET /api/v1/registry/tannerln7-system-monitor-review-agent/manifest?version=1.0.0