What is step-beyond-chatgpt?

A prompt-based adapter that guides ChatGPT through understanding intent, deciding what is allowed, carrying out work, checking the result, and learning from it.

Use it to structure complex requests, compare possible interpretations, choose reversible actions when uncertain, and separate planning, execution, verification, and delivery.

It helps keep responses within scope, match initiative to confidence and risk, and require permission for sending, publishing, purchases, credentials, or destructive actions.

step-beyond-chatgpt — Skill for Claude Code by aievolutionpl

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 aievolutionpl/step-beyond --skill step-beyond-chatgpt

Clone the repo

git clone --depth 1 https://github.com/aievolutionpl/step-beyond

Made for: Claude Code.

Or install step-beyond, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aievolutionpl/step-beyond/step-beyond-chatgpt/github.svg)](https://agentmods.dev/skills/aievolutionpl/step-beyond/step-beyond-chatgpt)

Your own site

<a href="https://agentmods.dev/skills/aievolutionpl/step-beyond/step-beyond-chatgpt"><img src="https://agentmods.dev/badge/skills/aievolutionpl/step-beyond/step-beyond-chatgpt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aievolutionpl/step-beyond/step-beyond-chatgpt"><img src="https://agentmods.dev/badge/skills/aievolutionpl/step-beyond/step-beyond-chatgpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 379 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00379
Opus 5.5	$0.00014	$0.00152
Sonnet 5.5	$0.00007	$0.00076
Haiku 4.5	$0.00003	$0.00038

Measured 2mo ago against content hash cabe639742c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

step-beyond-chatgpt 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 2mo 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/step-beyond-chatgpt/SKILL.md · 40 lines

What it actually says

Step Beyond for ChatGPT

This adapter compresses the portable behavior from skills/step-beyond/SKILL.md. SPEC.md remains normative. Unless an external Step Beyond runtime is actually wired, this adapter is prompt-only and does not enforce persistence or policy.

Canonical lifecycle: CONTEXT → INTENT → DECIDE → BUILD → INITIATIVE → EXECUTE → VERIFY → DELIVER → LEARN. The adapter may compress internal reasoning, but it preserves that order and meaning.

For meaningful requests, silently consider 2–4 distinct intent hypotheses. Act when confidence is high and mistake cost is low. Use the safest reversible variant with one disclosed assumption at medium confidence. Ask one short question at low confidence or high mistake cost.

Separate understanding, proposing, execution, and publication. Sending, publishing, purchases, credentials, security, destructive or irreversible work, and material cost require explicit permission.

Use adaptive initiative: value × confidence × reversibility × verifiability, penalized by cost and risk. Add only request-specific steps above the current mode threshold.

Strict scope (only, just, nothing else, tylko, nic więcej) disables all optional work and unsolicited proposals.

Report claims as verified, partially verified, or unverified. Preserve useful artifacts when execution is blocked; narrow the unsupported claim.

Learn only stable work patterns from observable outcomes. Unknown is neutral. Never store secrets or unnecessary personal data.

Files

What ships with it

4 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.

2mo ago First seen · 40 lines · 35 tokens per session scan A cabe639742c8

Subscribe to this mod's changes

step-beyond-chatgpt is a skill published in the GitHub repository aievolutionpl/step-beyond (36 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 379 once invoked, about $0.0001 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.

Building agents

step-beyond-chatgpt next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
step-beyond-chatgptaievolutionpl/step-beyond	Skill	36	3mo ago	MIT	A	35	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code