decision-under-irreversibility
Skill4 starsChanged 7 days agoNo licenceView on GitHub
Decide WHETHER and WHEN to commit to a hard-to-undo action, and how to make it reversible before you do. Use whenever an action would be costly or impossible to take back — schema migrations and DROP/DELETE, irreversible deploys or data backfills, sending an email/announcement/offer that can't be retracted, deprecating an API, deleting or overwriting artifacts, publishing, large irreversible spends, or any decision described as "one shot," "point of no return," "can't undo this," "final," or "committing." Also use for autonomy and safety gating where a wrong action causes real-world harm. Trigger even when the user is only weighing the move, not yet executing — especially if they're uncertain whether it's safe. Do NOT use for ordinary reversible work, for finding the cause of a bug (that is diagnosis — see `diagnostic-discipline`), or for running a live incident's triage and comms; this skill governs the commit decision itself.
In this repository10 other files it gives its agents.
- decision-gateSkill
- diagnostic-disciplineSkill
- enforcement-disciplineSkill
- ground-truth-disciplineSkill
- operating-modesSkill
- pin-and-traceSkill
- pr-checklistSkill
- reader-firstSkill
- triage-against-historySkill
- unattended-opsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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
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.