first-run-open

A first-run opening process for an app when a new user has not yet provided a real request. It shows a concrete starting idea and learns from the user's correction instead of presenting an empty prompt.

In plain words
What is it for?
Use it to tailor the opening to available user context and to choose a show-led approach for text or a say-led approach for voice.
Why use it?
It gives new users something specific to react to, helping them reach a useful goal faster when they do not know what to ask for.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/quantumbyteoss/quantumbyte/first-run-open
Any agent
npx skills add QuantumByteOSS/quantumbyte --skill first-run-open
Clone the repo
git clone --depth 1 https://github.com/QuantumByteOSS/quantumbyte

Made for: Claude Code, Codex.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00102 $0.00917
Opus 5 $0.00051 $0.00458
Sonnet 5 $0.00020 $0.00183
Haiku 4.5 $0.00010 $0.00092

Measured 3d ago against content hash 32976f7f7eb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

first-run-open 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 3d 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.

apps/worker/shared/prompts/agents/main_agent/skills/first-run-open/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First-Run — the opening

The opening's job: get to a substantive, qualifiable intent without ever facing the user with a blank box. Show a guess; the correction is the data.

Posture by modality (set this first)

  • Textshow-led. Lead with the visible sketch and tappable starting-point chips. A blank text field is the highest-drop-off move there is.
  • Voicesay-led. Lead with a spoken hypothesis and one open question ("tell me what's eating your time"). Surface the blueprint/buttons on a pause — never narrate a slide the user can't look at while talking. Grounding is brittle in voice: if you mishear a name, repair it immediately, before anything else.

Two entries

  • User-initiated (a real first message exists) → no cold-start needed. Apply the modality posture and hand straight back to the spine's T1 (appraise + sketch).
  • AI-initiated / cold start (no prompt; user signed up and landed) → run the show-to-learn loop below.

Cold start: show a provisional dream + a guess about the person

Branch on passive context:

  • Context-rich (firmographics resolved — company, industry from get_user_context): render a provisional Dream Preview — a concrete sketch from the firmographics — and a hypothesis about who they are. "I pulled up — looks like a . Most s your size lose the most time to , so here's a starting sketch. I'm guessing you run the — close? And is that the real headache, or something else?"
  • Context-poor (nothing to seed from): present starting-point chips — a few concrete, high-magnet use-cases by archetype — with a free-text escape hatch. Recognition over recall; never "what do you want to build?"

The first preview is provisional by design. Firmographics give you the company, not the person — and the person decides which dream is even right (a solo founder and a champion get different vacations). Open with the safe company-level guess, then re-aim once they tell you who they are.

Read the full file on GitHub · 47 lines

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. 3d ago First seen · 47 lines · 102 tokens per session scan A 32976f7f7eb1

Subscribe to this mod's changes

first-run-open is a skill published in the GitHub repository QuantumByteOSS/quantumbyte (322 stars, last pushed 21d ago), licensed Apache-2.0. It adds 102 tokens to every session and 917 once invoked, about $0.0005 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

gsd

Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents.

allgpt-co/QuickVoice · 23 tokens

st-full-workflow

Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…

e0ipso/strikethroo · 90 tokens

st-execute-blueprint

Use when the user asks to run, execute, implement, or carry out a Strikethroo plan or its blueprint by plan ID in this repository — triggers include execute blueprint, run the plan, implement plan, build the plan. Do not use to create a plan, to only generate tasks, to run a single task, or for generic development…

e0ipso/strikethroo · 82 tokens

st-generate-tasks

Use when the user asks to decompose, break down, or generate tasks for an existing Strikethroo plan ID in this repository — triggers include generate tasks, break down the plan, decompose plan, create the task blueprint. Do not use to create a new plan, to execute tasks, or for generic project planning outside…

e0ipso/strikethroo · 77 tokens

st-code-review

Use when the blueprint execution gate asks for an independent second-harness review of a Strikethroo plan's cumulative diff in this repository — triggers include code review gate, review the plan diff, second-model review, CODEREVIEW hook, review the cumulative diff. Do not use to review a single task, to review code…

e0ipso/strikethroo · 87 tokens

st-execute-task

Use when the user asks to run, execute, or implement one specific task ID within a Strikethroo plan in this repository — triggers include execute task, run task, implement task, do task N. Do not use to execute a whole plan or blueprint, to generate tasks, or for generic development outside Strikethroo.

e0ipso/strikethroo · 72 tokens