agentleFS
Sign inStart free
jitanguptajitangupta/file-safety-guard/skills/dry-run/SKILL.md

dry-run

Skill3 starsChanged 9 months agoMITView on GitHub

Plan-first execution for multi-step file operations. Use when a task involves more than 2 file operations or when the user explicitly asks for a dry run. Creates a plan.md file listing all planned changes, waits for user approval before executing, and updates the plan with actual results after completion.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. marcusgoll/Spec-Flow★ 94same name
    2. dynos-fit/dynos-work★ 2same name
    3. atinder-harika/reel-reactor★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No surprises — you see the plan before anything happens.

    line 12
  2. Distinctive:

    If the user did request deletions, list each file with its full path.

    line 55
  3. Distinctive:

    After creating and showing the plan, stop and wait.

    line 59
  4. Distinctive:

    Only proceed when the user says one of: "go ahead", "proceed", "approved", "yes", "do it", or similar explicit confirmation.

    line 60
  5. Very specific:

    If the user requests changes to the plan, update plan.md and show it again before proceeding.

    line 61
  6. Very specific:

    After all operations are complete, update plan.md with an Execution Log section:

    line 65

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dry Run — Plan First, Act Later

No surprises — you see the plan before anything happens.

Rules

1. When to Create a Plan

  • For any task that involves more than 2 file operations, create a plan.md file in the working directory BEFORE executing anything.
  • A "file operation" includes: creating, modifying, moving, renaming, or deleting a file.

2. What the Plan Must Include

The plan.md file must contain these sections:

# Operation Plan

**Task:** [Brief description of what was requested]
**Date:** [YYYY-MM-DD HH:MM]

## Files to be Created
- filename.ext — purpose/description

## Files to be Modified
- filename.ext — what will change

## Files to be Moved or Renamed
- old/path/filename.ext → new/path/filename.ext

## Files to be Deleted
- NONE (unless explicitly requested by the user)

## Summary
[1-2 sentence overview of what will change]

---

## Execution Log
_To be filled after execution_

3. Deletion Default

  • The "Files to be Deleted" section should always say NONE unless the user has specifically and explicitly asked for file deletion.
  • If the user did request deletions, list each file with its full path.

4. Wait for Approval

  • After creating and showing the plan, stop and wait.
  • Only proceed when the user says one of: "go ahead", "proceed", "approved", "yes", "do it", or similar explicit confirmation.
  • If the user requests changes to the plan, update plan.md and show it again before proceeding.

5. Post-Execution Update

After all operations are complete, update plan.md with an Execution Log section:

## Execution Log
**Executed at:** 2026-02-09 14:45
**Status:** Complete

- ✅ Created: report.docx
- ✅ Modified: index.html (updated header section)
- ⚠️ Skipped: styles.css (no changes needed after review)
- ✅ Backup created: _backups/index_backup_20260209_1445.html

Activation

This skill activates when:

  • A task involves more than 2 file operations
  • The user explicitly asks for a dry run or plan
  • A complex multi-file operation is requested

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free