code-writer

Delegate boilerplate code generation to a cheap Gemini model.

IndexedApache-2.0

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/matijalekovic-code-writer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Delegate boilerplate code generation to a cheap Gemini model. Use for tests, config, docstrings, type stubs, or any generation where >80% is predictable from reference files.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/code-writer

What's inside

Skill name: code-writer
Description: Delegate boilerplate code generation to a cheap Gemini model. Use for tests, config, docstrings, type stubs, or any generation where >80% is predictable from reference files.
License: Apache-2.0
Instructions: 17 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

```bash
# Generate and write directly to target file
${CLAUDE_PLUGIN_ROOT}/scripts/code-write --spec "<what to generate>" --reference <reference-file> --target <output-path>

# Output to stdout instead (omit --target)
${CLAUDE_PLUGIN_ROOT}/scripts/code-write --spec "<what to generate>" --reference <reference-file>
```

Each call is independent. To build on what was just generated, pass that file as the
`--reference` for the next call.

If the script warns that the answer was truncated (`finishReason: MAX_TOKENS`), the
generated file is incomplete — re-run with a narrower spec or a higher
`SHUNT_MAX_OUTPUT_TOKENS`, don't patch around the cut.

Review the output and make surgical edits for the ~5-20% that needs Claude-level judgment.

From matijalekovic/token-optimization-gemini-shunt, Apache-2.0.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Sep 7, 2026 (1 month ago)
Last release: Sep 7, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/matijalekovic/token-optimization-gemini-shunt
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql