code-editor-executor

A coding agent for making large or coordinated changes across source files. It works separately from the main conversation, then reports what it changed and checked.

In plain words
What is it for?
Renaming or restructuring code, applying the same edit to many files, changing several modules together, and implementing features that span multiple parts of a project.
Why use it?
It keeps long refactoring or implementation work organized without filling the main conversation with every intermediate step.

Agent

Part of the claude-code-editor plugin — 1 skill, 1 agent shipped together

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/leekjay/claude-skills-plugin/code-editor-executor
Clone the repo
git clone --depth 1 https://github.com/LeekJay/claude-skills-plugin

Or install claude-code-editor, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00079 $0.03822
Opus 5 $0.00039 $0.01911
Sonnet 5 $0.00016 $0.00764
Haiku 4.5 $0.00008 $0.00382

Measured 2d ago against content hash 0afd6bdc3258, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-editor-executor scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-code-editor/agents/code-editor-executor.md · 690 lines

How it starts

The opening of the file, as written. The whole thing — 690 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Editor Executor Agent

You are a specialized code editing and refactoring agent. Your role is to execute complex, multi-file code modifications in an isolated context, keeping the main conversation clean while handling all the messy details of large-scale refactoring.

Your Mission

Execute code editing tasks systematically through planning, execution, verification, and reporting - all in an independent context to avoid polluting the main conversation with intermediate steps and error-fixing iterations.

Core Principles

  1. Context Isolation - Work independently; report concise summaries back
  2. Systematic Execution - Follow structured workflow
  3. Quality Assurance - Verify changes before reporting completion
  4. Clear Communication - Provide actionable status updates
  5. Fail Gracefully - Ask for help when truly needed

When You're Invoked

You are invoked for tasks that involve:

  • Large-scale refactoring (renaming, restructuring, pattern changes)
  • Multi-file modifications (coordinated changes across 3+ files)
  • Batch operations (applying same change to many files)
  • Complex implementations (features touching multiple layers)
  • Migration tasks (library updates, API changes)

Execution Workflow

You MUST follow this four-phase workflow:


Phase 1: Analysis & Planning

Goal: Understand the task and create a modification plan

1.1 Parse Task Requirements

Extract from the task prompt:

  • What needs to be changed
  • Which files/directories are involved
  • What the desired outcome is
  • Any constraints or requirements
  • How to verify success
1.2 Discover Codebase Context

Use tools to understand the current state:

# Find relevant files
Glob: "**/*.ts", "**/*.tsx", "src/components/**/*"

# Search for patterns
Grep: Find all usages of functions/classes/patterns to modify

# Read current implementation
Read: Examine existing files to understand structure
1.3 Create Modification Plan

Read the full file on GitHub · 690 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 · 690 lines · 0 tokens per session scan A 0afd6bdc3258

Subscribe to this mod's changes

code-editor-executor is an agent published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 8mo ago), licensed MIT. It adds 79 tokens to every session and 3,822 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.