flowx: Command for Claude Code

.claude/commands/hooks/pre-edit.md

pre-edit is a command for Claude Code from sethdford/flowx. It costs 0 tokens per session (550 once invoked), scanned A, a copy of pre-edit, MIT.

A pre-edit check that runs before an agent changes a file. It can validate syntax, look for merge conflicts, make a backup, and assign a suitable agent.

In plain words
What is it for?
Use it before editing source, configuration, database, or test files when you want checks, automatic agent assignment, conflict detection, or a backup.
Why use it?
It catches some problems before edits begin and can reduce the risk of losing work or creating conflicts.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is sethdford/flowx's own configuration. It tells Claude Code how to work on flowx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flowx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sethdford/flowx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sethdford/flowx/main/.claude/commands/hooks/pre-edit.md
Clone the repo
git clone --depth 1 https://github.com/sethdford/flowx

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pre-edit

README.md
[![agentmods](https://agentmods.dev/badge/commands/sethdford/flowx/pre-edit/github.svg)](https://agentmods.dev/commands/sethdford/flowx/pre-edit)
Your own site
<a href="https://agentmods.dev/commands/sethdford/flowx/pre-edit"><img src="https://agentmods.dev/badge/commands/sethdford/flowx/pre-edit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pre-edit

Your own site · 80×15
<a href="https://agentmods.dev/commands/sethdford/flowx/pre-edit"><img src="https://agentmods.dev/badge/commands/sethdford/flowx/pre-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.00550
Opus 5.5 $0.00000 $0.00220
Sonnet 5.5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 1mo ago against content hash 2fb4dd587d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-edit 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 1mo 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.

Origin

This is a copy

100% identical to pre-edit — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/hooks/pre-edit.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hook pre-edit

Execute pre-edit validations and agent assignment before file modifications.

Usage

npx claude-flow hook pre-edit [options]

Options

  • --file, -f <path> - File path to be edited
  • --auto-assign-agent - Automatically assign best agent (default: true)
  • --validate-syntax - Pre-validate syntax before edit
  • --check-conflicts - Check for merge conflicts
  • --backup-file - Create backup before editing

Examples

Basic pre-edit hook

npx claude-flow hook pre-edit --file "src/auth/login.js"

With validation

npx claude-flow hook pre-edit -f "config/database.js" --validate-syntax

Manual agent assignment

npx claude-flow hook pre-edit -f "api/users.ts" --auto-assign-agent false

Safe editing with backup

npx claude-flow hook pre-edit -f "production.env" --backup-file --check-conflicts

Features

Auto Agent Assignment

  • Analyzes file type and content
  • Assigns specialist agents
  • TypeScript → TypeScript expert
  • Database → Data specialist
  • Tests → QA engineer

Syntax Validation

  • Pre-checks syntax validity
  • Identifies potential errors
  • Suggests corrections
  • Prevents broken code

Conflict Detection

  • Checks for git conflicts
  • Identifies concurrent edits
  • Warns about stale files
  • Suggests merge strategies

File Backup

  • Creates safety backups
  • Enables quick rollback
  • Tracks edit history
  • Preserves originals

Integration

This hook is automatically called by Claude Code when:

  • Using Edit or MultiEdit tools
  • Before file modifications
  • During refactoring operations
  • When updating critical files

Manual usage in agents:

# Before editing files
npx claude-flow hook pre-edit --file "path/to/file.js" --validate-syntax

Output

Returns JSON with:

{
  "continue": true,
  "file": "src/auth/login.js",
  "assignedAgent": "auth-specialist",
  "syntaxValid": true,
  "conflicts": false,
  "backupPath": ".backups/login.js.bak",
  "warnings": []
}

Read the full file on GitHub · 102 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. 1mo ago First seen · 102 lines · 0 tokens per session scan A 2fb4dd587d59

Subscribe to this mod's changes

pre-edit is a command published in the GitHub repository sethdford/flowx (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 550 tokens. A static security scan graded it A with 0 findings. It is 100% identical to pre-edit, differing in 12 lines, and is treated as a copy.