Open Steps is a collection of coding-agent skills that explain development sessions, decisions, results, and next steps in plain language. It is intended for people who use agents to build software but do not want to rely on engineering jargon, and supports Claude Code, Codex, Cursor, and Gemini CLI. The catalogue entries provide the skills, hooks, plugin, and command that make up this workflow.
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.
npx skills add kharmanskyi/open-steps --skill os-what-could-go-wronggit clone --depth 1 https://github.com/kharmanskyi/open-stepsWrote 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.
[](https://agentmods.dev/skills/kharmanskyi/open-steps/os-what-could-go-wrong)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00149 | $0.01801 |
| Opus 5.5 | $0.00060 | $0.00720 |
| Sonnet 5.5 | $0.00030 | $0.00360 |
| Haiku 4.5 | $0.00015 | $0.00180 |
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 24d 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.
How it starts
The opening of the file, as written. The whole thing — 151 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.
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
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.
- Look it up yourself. Documents, data, the repository, the last report
in
~/.claude/open-steps/reports/, what went wrong last time. - Ask, but earn the ask. Only a gap where guessing wrong would change the
verdict, one question at a time through
os-ask-simple, three at most. Nobody there to answer, or an answer that would not move the verdict -> 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".
What ships with it
5 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.
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.
- 24d ago Changed eaf65a144a47
- 1mo ago Changed · +1 lines 56b1d7633dbc
- 1mo ago Changed 8110d9ffc4b1
- 1mo ago Changed · -18 lines 117864813b48
- 1mo ago First seen · 168 lines · 149 tokens per session scan A c0aafcee31a3
os-what-could-go-wrong is a skill published in the GitHub repository kharmanskyi/open-steps (1,184 stars, last pushed 20d ago), licensed MIT. It adds 149 tokens to every session and 1,801 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
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.
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.
learn-codebase
Socratic tutor that teaches codebase understanding through questioning, challenges, and active recall. Invoke with /learn-codebase when onboarding to a new codebase or deepening understanding of existing code. Maintains a learning journal that tracks mastery and schedules reviews.
cinematic-scroll
Design and build cinematic websites, 3D websites, interactive portfolios and product landing pages with scroll-driven storytelling, parallax, text animation and optional Three.js/WebGL scenes. Use for new experiences, motion improvements, scroll audits and storyboards in standalone HTML or an existing app. Includes…
deepread-api
Full DeepRead API reference. All endpoints, auth, request/response formats, blueprints, webhooks, error handling, and code examples for OCR, structured extraction, form filling, and PII redaction.
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.