agentleFS
26zl26zl/universal-agent-skills/skills/destructive-ops-approval/SKILL.md

destructive-ops-approval

Skill2 starsChanged 39 days agoMITView on GitHub

Obtain explicit confirmation before irreversible or outward-facing operations such as force-pushes, history rewrites, mass deletion, data migrations, or production changes, and prefer the reversible alternative when one exists. Use when an action could destroy data, rewrite shared history, or change systems other people depend on; do not use to stall routine, easily reversible work.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before force-pushing, rewriting shared history, deleting branches or tags others may use, mass-deleting files or records, dropping schemas, …

    line 13
  2. Distinctive:

    Prefer the reversible form when one exists: soft deletes, archives, expiring backups, feature flags, force-with-lease over force, dry run …

    line 15
  3. Distinctive:

    If the target's state does not match what the approval assumed, stop and re-confirm instead of proceeding.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Destructive Ops Approval

Irreversible actions get a human decision first, every time.

Rules

  • Before force-pushing, rewriting shared history, deleting branches or tags others may use, mass-deleting files or records, dropping schemas, or changing production configuration, state the action, the blast radius, and the rollback plan, then wait for explicit approval.
  • Approval covers one action in one context; it does not carry over to the next occasion or a wider scope.
  • Prefer the reversible form when one exists: soft deletes, archives, expiring backups, feature flags, force-with-lease over force, dry run before apply.
  • Take a verified backup or snapshot before an approved destructive step, and confirm the restore path works.
  • Scope credentials and commands to the narrowest target that completes the task; never widen a destructive command to save a step.
  • If the target's state does not match what the approval assumed, stop and re-confirm instead of proceeding.

Boundaries

  • Routine local, reversible operations need no ceremony.
  • Organizational emergency procedures override this skill's pacing; follow them exactly.

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.