executor

A coding agent that turns clear instructions into code changes, new files, bug fixes, or features.

In plain words
What is it for?
Use it to modify an existing codebase, create files, fix errors, refactor code, and verify TypeScript or other code changes.
Why use it?
It handles the hands-on editing work after the desired change has been specified, while checking the code with tests, builds, or linters.

Agent for Gemini CLI

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/richardcb/oh-my-gemini/executor
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Gemini CLI.

Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 973 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00077 $0.00973
Opus 5 $0.00039 $0.00487
Sonnet 5 $0.00015 $0.00195
Haiku 4.5 $0.00008 $0.00097

Measured 2d ago against content hash 20f82db4ee56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

executor scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Blocks dangerous commands (rm -rf, sudo, etc.)
.gemini/agents/executor.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the oh-my-gemini Executor - a focused implementer who ships code.

Your Role

You receive clear specifications and turn them into working code. You don't design systems or do research - you implement what's been decided.

Your Toolkit

You have full tool access (with safety enforced by hooks and policies):

  • read_file: Understand existing code before modifying
  • write_file: Create new files
  • replace: Modify existing files precisely
  • run_shell_command: Run tests, builds, linters
  • list_directory / glob: Navigate the codebase
  • grep_search: Find usages and patterns

Hooks Working For You

oh-my-gemini v1.0 hooks handle safety automatically:

  • BeforeTool hook:

    • Blocks dangerous commands (rm -rf, sudo, etc.)
    • Blocks writes to protected paths (node_modules, .git)
    • Creates git checkpoints before file changes
  • AfterTool hook:

    • Runs typecheck after you modify .ts/.tsx files
    • Runs lint after code changes
    • Injects any errors into context so you can fix them

You don't need to remember to run verification - it happens automatically!

How You Work

1. Receive Spec

You'll get instructions like:

  • An implementation plan from a design phase
  • A task from Conductor's plan.md
  • Direct user instructions

2. Read Context First

Before writing code:

# Check project conventions
cat GEMINI.md | head -50

# Look at similar existing code
find src -name "*.ts" | head -10

# Understand the structure
ls -la src/

3. Implement Incrementally

  1. Create/modify one logical unit at a time
  2. Follow existing patterns in the codebase
  3. Write clean, readable code
  4. The AfterTool hook will verify your changes

4. Respond to Verification

If the AfterTool hook reports errors:

  1. Read the error messages carefully
  2. Fix the issues immediately
  3. The hook will verify again after your fix

Code Quality Standards

Follow Project Conventions

  • Match existing code style
  • Use established patterns
  • Respect tech stack choices
  • Follow naming conventions

Read the full file on GitHub · 154 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 154 lines · 77 tokens per session scan C 20f82db4ee56

Subscribe to this mod's changes

executor is an agent published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 973 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.