os-what-could-go-wrong

os-what-could-go-wrong is a skill for Claude Code from kharmanskyi/open-steps. It costs 149 tokens per session (1,925 once invoked), scanned A, original, MIT.

A premortem and red-team review for decisions that are difficult to undo, such as contracts, purchases, migrations, launches, price changes, or reorganisations. It imagines the decision has failed and works backward to identify why.

In plain words
What is it for?
Use it to challenge a planned commitment, look for failure scenarios, and identify weaknesses before taking an irreversible step.
Why use it?
It exposes risks and missing considerations while there is still time to change the decision.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the open-steps plugin — 7 skills, 1 command, 2 hooks shipped together

Good fit Use it to challenge a planned commitment, look for failure scenarios, and identify weaknesses before taking an irreversible step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kharmanskyi/open-steps/os-what-could-go-wrong
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kharmanskyi/open-steps --skill os-what-could-go-wrong
Clone the repo
git clone --depth 1 https://github.com/kharmanskyi/open-steps

Made for: Claude Code.

Or install open-steps, the plugin that ships this one along with the rest of its 7 skills, 1 command, 2 hooks.

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 os-what-could-go-wrong

README.md
[![agentmods](https://agentmods.dev/badge/skills/kharmanskyi/open-steps/os-what-could-go-wrong/github.svg)](https://agentmods.dev/skills/kharmanskyi/open-steps/os-what-could-go-wrong)
Your own site
<a href="https://agentmods.dev/skills/kharmanskyi/open-steps/os-what-could-go-wrong"><img src="https://agentmods.dev/badge/skills/kharmanskyi/open-steps/os-what-could-go-wrong/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 os-what-could-go-wrong

Your own site · 80×15
<a href="https://agentmods.dev/skills/kharmanskyi/open-steps/os-what-could-go-wrong"><img src="https://agentmods.dev/badge/skills/kharmanskyi/open-steps/os-what-could-go-wrong.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 32
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found 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 $0.00149 $0.01925
Opus 5 $0.00075 $0.00962
Sonnet 5 $0.00030 $0.00385
Haiku 4.5 $0.00015 $0.00193

Measured 9d ago against content hash c0aafcee31a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

os-what-could-go-wrong 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 9d 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.

skills/os-what-could-go-wrong/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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. This skill writes the brief, hands it over, and passes the answer back without softening it.

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 agent you dispatch cannot see this conversation and does not inherit the writing style, so the language has to travel with the handover - see step 2.

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
What it is for: the problem it solves, and what success looks like, measured
  wherever it can be
The main moves: the money, the people, the systems, the dates
What is fixed: the constraints, plus the surrounding facts that matter
Who it lands on: who and what is affected if this goes wrong
What cannot be undone: which parts are one-way
When we would know: the date success or failure actually gets judged
What we know: facts from documents, data, the repository, past incidents,
  each with where it came from
What we are assuming: every gap nobody could close, written as an assumption

Close the gaps in this order, and stop as soon as a gap is closed.

  1. Look it up yourself. Documents, data, the repository, the last report in ~/.claude/open-steps/reports/, what went wrong last time.
  2. Ask, but earn the ask. Only a gap where guessing wrong would change the verdict is worth the user's attention, and the pack's own rule holds here: one question at a time, through os-ask-simple. Three is plenty. Nobody there to answer, or an answer that would not move the verdict -> skip straight to 3.
  3. Write the guess down as a guess. Put the assumed value in its line, mark it (assumed), and repeat it under "What we are assuming".

Read the full file on GitHub · 168 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 168 lines · 149 tokens per session scan A c0aafcee31a3

Subscribe to this mod's changes

os-what-could-go-wrong is a skill published in the GitHub repository kharmanskyi/open-steps (305 stars, last pushed 2d ago), licensed MIT. It adds 149 tokens to every session and 1,925 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

命理解读师

A Chinese-language Zi Wei Dou Shu birth-chart interpretation guide, a form of traditional Chinese astrology based on birth details. It presents results as possible patterns rather than certain predictions and can include a chosen year's outlook.

learnwithu/mingli-master · 189 tokens

travel-plan-viz

A tool that turns a travel plan into a single HTML page designed for phones and offline reading. The page can include an interactive map, a daily timeline, and reminders to book things before departure.

zexuanw958-svg/travel-plan-viz · 96 tokens

cinematic-scroll

Build or improve cinematic websites with scroll-driven storytelling, pinned reveals, parallax, kinetic type, and optional 3D. Deliver standalone HTML or integrate into an existing app, with mobile and reduced-motion fallbacks and browser evidence. Also supports scroll audits and motion storyboards. Use for cinematic…

MustBeSimo/cinematic-scroll-skill · 75 tokens

Linear

Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

wrsmith108/linear-claude-skill · 32 tokens

gpt-image2-ppt

A tool for creating presentation slides as high-resolution images and packaging them into a 16:9 PowerPoint file. It turns a Markdown outline or slide plan into a styled deck using OpenAI image generation.

JuneYaooo/gpt-image2-ppt-skills · 112 tokens

majia-guanyuan

A practical extension layer for Guandata BI, a business-intelligence platform used to query data, build charts, and publish dashboards. It covers advanced data-pipeline work and custom HTML, CSS, and JavaScript dashboards beyond the standard tools.

maojiebc/majia-guanyuan · 498 tokens