os-what-could-go-wrong SKILL.md skillA

os-what-could-go-wrong from kharmanskyi/open-steps is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kharmanskyi/open-steps/os-what-could-go-wrong@git:20260930.7e255d1

Pins git:20260930.7e255d1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kharmanskyi/open-steps
Path
skills/os-what-could-go-wrong/SKILL.md
Versions recorded
5
Latest version
git:20260930.7e255d1, committed Sep 30, 2026
First version recorded
Aug 29, 2026
Size
7,357 bytes
Repository stars
1,290
License
MIT

ALWAYS invoke this skill before anything hard to undo gets agreed to - a contract, a purchase, a migration, a launch, a price change, a reorganisation - and whenever the user asks "what could go wrong", "what are we missing", "poke holes in this", or for a premortem or a red team, in any language. Assumes the decision already failed and works backwards to find out why, in a fresh agent that had no hand in making it. Sweeps nine areas and shows what each produced, including the empty ones. Ends…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# os-what-could-go-wrong

Assume it already failed, then work backwards to find out why - while there is
still time to change it. The attack runs in a fresh agent that had no part in
the decision, because an agent that helped shape one reviews it far too
gently: it defends its own reasoning, and it misses the thing that kills the
plan out of politeness.

`os-ask-simple` screens a choice before the user picks one. This one runs
after the choice is made and before it can no longer be taken back.

## Language

Write in the language the user speaks in this session, detected from the
conversation. Names, figures and identifiers stay as they are. The fresh
agent cannot see this conversation, so the language travels in the handover.

## Step 1 - write down what is actually being decided

Find the decision first. Given as text or a document, that is it. Asked at the
end of a discussion, it is the decision the discussion arrived at, and say
which one you took it to be. If neither, ask which decision to attack.

Then fill every line. This is the only thing the fresh agent will ever see.

```
DECISION BRIEF
What will be done: three to seven sentences
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kharmanskyi/open-steps/os-what-could-go-wrong@sha256:eaf65a144a472e7b

The line at the top of this page pins the label git:20260930.7e255d1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wcpl6lsou2yiuypg.svg)](https://markdownregistry.com/a/art_wcpl6lsou2yiuypg)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 29, 2026 and Sep 30, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260930.7e255d1 latest2026-09-30 7e255d1 7,357 BA view · diff
git:20260914.a61b0d62026-09-14 a61b0d6 7,323 BA view · diff
git:20260913.7c87cdb2026-09-13 7c87cdb 7,095 BA view · diff
git:20260911.23d17a12026-09-11 23d17a1 7,097 BA view · diff
git:20260829.340e7d02026-08-29 340e7d0 7,902 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7357 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kharmanskyi/open-steps · 1,290 stars · license MIT · pushed 2026-10-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wcpl6lsou2yiuypg
GET https://markdownregistry.com/api/v1/resolve?ref=kharmanskyi/open-steps/os-what-could-go-wrong
GET https://markdownregistry.com/api/v1/blob/eaf65a144a472e7b4b2208b6495dcf7bdf77ebee68c2007fe67f5f268b7e7375

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kharmanskyi/open-steps

os-ask-simple SKILL.md skill
kharmanskyi/open-steps · skills/os-ask-simple/SKILL.md · ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be…
git:20261005.212790e · audit A · 1,290 stars
os-big-picture SKILL.md skill
kharmanskyi/open-steps · skills/os-big-picture/SKILL.md · ALWAYS invoke this skill when the user asks where the project as a whole stands - "where are we", "what's the big…
git:20261004.d7bdad8 · audit A · 1,290 stars
os-check-work SKILL.md skill
kharmanskyi/open-steps · skills/os-check-work/SKILL.md · ALWAYS invoke this skill when the user asks about work done outside this session - "check work", "check the others"…
git:20260930.7e255d1 · audit A · 1,290 stars
os-done-or-not SKILL.md skill
kharmanskyi/open-steps · skills/os-done-or-not/SKILL.md · ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what…
git:20260930.7e255d1 · audit A · 1,290 stars
os-say-simple SKILL.md skill
kharmanskyi/open-steps · skills/os-say-simple/SKILL.md · ALWAYS invoke this skill when the user asks for simpler or shorter about something said or written - "say it simply"…
git:20260930.7e255d1 · audit A · 1,290 stars
os-step-by-step SKILL.md skill
kharmanskyi/open-steps · skills/os-step-by-step/SKILL.md · ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever…
git:20260930.7e255d1 · audit A · 1,290 stars
os-whats-next SKILL.md skill
kharmanskyi/open-steps · skills/os-whats-next/SKILL.md · ALWAYS invoke this skill when the user asks what to do next, what is left, or what is blocked - "what's next", "what…
git:20260930.7e255d1 · audit A · 1,290 stars

Every file in kharmanskyi/open-steps

Browse by kind, by grade A, or by owner.