code-agent

Code Agent

Quick Reference — see parent for full agent ecosystem.

The Code Agent converts specs and plans into working, tested code. It reads requirements or a plan JSON, produces implementation across multiple files, writes companion tests, and iterates until all verification gates pass. Its primary contract is correctness: the output must compile, pass tests, and follow project conventions.

When Not to Use

• Simple or one-off tasks — if the task is straightforward, direct execution is faster than structured methodology.
• Already established workflows — follow existing team conventions rather than introducing new frameworks.
• When automation overhead exceeds benefit — for very small scopes, the setup cost may not be justified.

Dependencies

• Python 3.8+ or Node.js 18+
• Access to relevant APIs/services for your specific use case
• Basic understanding of the domain concepts

Commands

# Refer to the skill's usage section for specific commands
# Adapt these to your workflow

Key Responsibilities

• Read specs, write code: Accept structured plans or natural-language requirements and produce production-ready implementation across the defined file boundaries
• Own the test suite: Generate unit, integration, and regression tests alongside every code change — coverage targets are non-negotiable
• Iterate on verification: Run linters, type checks, and tests after every write cycle; fix failures before declaring done

Code Example

"""Minimal code agent pattern — implement from plan."""

import json, subprocess, sys
from pathlib import Path

def implement(plan_path: str, output_dir: str) -> dict:
    plan = json.loads(Path(plan_path).read_text())
    changed = []

    for step in plan["steps"]:
        for file_spec in step.get("files", []):
            # Read existing file or create new
            path = Path(output_dir) / file_spec["path"]
            if path.exists():
                original = path.read_text()
            else:
                original = ""

            # Apply the implementation (simplified — real agent calls an LLM)
            new_code = f"# {file_spec['path']}\n# {file_spec['description']}\n{original}"
            path.write_text(new_code)
            changed.append(str(path))

    # Write tests
    for spec in plan.get("tests", []):
        test_path = Path(output_dir) / spec["path"]
        test_path.write_text(f"# Test for {spec['target']}\ndef test_{spec['name']}():\n    assert True\n")
        changed.append(str(test_path))

    return {"files_changed": changed, "tests_written": len(plan.get("tests", []))}

if __name__ == "__main__":
    result = implement(sys.argv[1], sys.argv[2])
    print(json.dumps(result, indent=2))