AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Coding Agent

skill-avivk5498-golem-coding-agent · by AvivK5498

Delegate coding tasks to Claude Code. Use when: building features, creating handlers, refactoring, reviewing PRs, iterative coding. NOT for: simple file edits (use filesystem), or quick config changes (use config_update).

No reviews yet
0 installs
52 views
0.0% view→install

Install

$ agentstack add skill-avivk5498-golem-coding-agent

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-avivk5498-golem-coding-agent)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Coding Agent? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Coding Agent

Delegate coding work to Claude Code via the code_agent tool. You are the orchestrator — describe the task, let the coding agent execute.

When to Use

  • Building new features, handlers, or scripts
  • Refactoring or restructuring code across multiple files
  • Creating new skills with scripts/
  • Reviewing PRs or analyzing codebases
  • Any task that requires reading multiple files, writing code, and running tests
  • Installing dependencies (npm install, bun add)
  • Running tests (bun test)

When NOT to Use

  • Simple file reads/edits -> use workspace tools
  • Config changes -> use config_update
  • Quick shell commands (git, curl) -> use run_command

How to Use

Basic Task

code_agent(
  task: "Build a health-check handler in src/scheduler/handlers/health-check.ts that pings an endpoint every 30 seconds and alerts the user if it returns non-200.",
  effort: "low"
)

Effort Levels

| Effort | Model | Best for | |--------|-------|----------| | low (default) | Claude Sonnet | Single-file edits, small fixes, tests, config changes | | high | Claude Opus | Multi-file features, complex refactors, deep debugging |

Good Task Descriptions

Be specific. Include:

  1. What to build (feature, handler, script)
  2. Where to put it (file path)
  3. Pattern to follow (reference existing code)
  4. How to test (run tests, verify output)

Good: > "Create a TypeScript job handler in src/scheduler/handlers/health-check.ts that polls https://example.com/health every 30 seconds. If non-200, return the error as the job result. Follow the JobHandler pattern from existing handlers. Include error handling."

Bad: > "Build me a health checker"

Platform-Specific Patterns

Creating a New Handler (auto-loaded)

Handlers in src/scheduler/handlers/ are hot-reloaded. The coding agent should:

  1. Read an existing handler as a reference
  2. Create a new handler file implementing the JobHandler interface
  3. Export it as a named export
  4. The job-worker picks it up automatically — no restart needed

Creating a New Skill

Skills in skills/ are also hot-loaded. The coding agent should:

  1. Read skills/skill-creator/SKILL.md for the format
  2. Create skills//SKILL.md with YAML frontmatter
  3. Optionally add scripts/, references/, assets/ subdirectories
  4. The skill loader picks it up within 30 seconds

Rules

  1. You are the orchestrator — do NOT hand-code patches yourself. Delegate to code_agent.
  2. If the agent fails — explain what went wrong. Do not silently take over and write the code yourself.
  3. Be patient — coding tasks take 10-120 seconds. Wait for the result.
  4. Report back — after code_agent finishes, summarize what was built and whether it needs a restart.
  5. Working directory matters — always set cwd to the project root so the agent has full context.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.