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 agentmods add commands/kaelsensei/magicaibuilder/create-user-guidegit clone --depth 1 https://github.com/KaelSensei/MagicAIBuilderWrote 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/commands/kaelsensei/magicaibuilder/create-user-guide)<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/create-user-guide"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/create-user-guide.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00903 |
| Opus 5 | $0.00000 | $0.00451 |
| Sonnet 5 | $0.00000 | $0.00181 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
create-user-guide 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create User Guide – Initial User Guide Generation
When /create-user-guide is invoked, generate or regenerate the user-facing documentation for the app so end users know how to use it.
Step 1: Load Project Context
- Assume the project root as the working directory
- Read the following to understand current app behavior:
PROGRESS.md– completed features and phasesCHANGELOG.md– what was added/changed (user-relevant)README.md– overview and quick startFeatures.md(if present) – feature specs and flows
- Optionally skim main screens/components (e.g.
src/screens/*.tsx) to capture navigation and flows
Step 2: Define the User Guide Scope
The user guide is for end users, not developers. It should cover:
- Getting started: How to open the app, first-time experience
- Main flows: Home, viewing balance and transactions, adding/editing transactions
- Accounts: Managing accounts (add, edit, archive)
- Budgets: Creating and viewing budgets, understanding over-budget alerts
- Settings: Accessing settings, export (CSV), optional AI/voice setup
- Voice input (if implemented): How to use voice to add a transaction, permissions, optional API key
Do not include:
- Internal architecture, database schema, or code structure
- Developer-only setup (unless a short “Optional: AI key” style note for voice)
Step 3: Create USER_GUIDE.md
- Create or overwrite
USER_GUIDE.mdat the project root (same level as README.md, PROGRESS.md). - Structure (adapt to what the app actually has):
- Title and short intro (e.g. “Vayo – User Guide”)
- Last updated:
<date>at the top - Getting started – opening the app, first screen
- Home – total balance, date filters (All / Last 7 days / This month), recent transactions, over-budget alert, FAB “+ Add”
- Adding a transaction – manual form (amount, type, category, account, date, location, description, tags)
- Editing or deleting a transaction – tap transaction on Home → edit form, update or delete with confirmation
- Accounts – header “Accounts”, list, add account, edit account, archive account
- Budgets – where to open Budgets, create budget (category, max, period), list with spent vs max, over-budget on Home
- Settings – how to open (e.g. gear icon in header), export transactions (CSV), optional: Budgets link, voice/AI setup (e.g. API key in .env)
- Voice input (if applicable) – Speak button, permissions, transcript, “Parse & fill”, low-confidence hint
- Use clear headings, short step-by-step instructions, and user language (e.g. “Tap the gear icon” not “Invoke headerLeft”).
- If the app does not have a feature yet, omit that section or mark it as “Coming soon” where appropriate.
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.
- 5d ago First seen · 78 lines · 0 tokens per session scan A ffdf0d2cd040
create-user-guide is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 903 tokens. 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 2026-08-31.
Other commands, from other repositories
spec-plan
Step 4 of the Vibe-Spec workflow. Generate the high-level plan file for every phase in the V2 phase index, each with a scope + status header, so the user has a complete set of plan files to work from.
spec-phases
Step 3 of the Vibe-Spec workflow. Break the V1 spec into sequential, self-contained phases and append a phase index, producing the final V2 spec.
spec-secrets
Audit a Vibe-Spec app for secrets leaking to the browser. A locked-down, redacting command — a local script reads .env and the built bundle, and Claude only ever sees variable NAMES and pass/fail verdicts. Secret values never enter the model's context.
spec-doctor
Read-only environment health check for the Vibe-Spec stack. Detects your OS and reports which prerequisite tools (Git, Node, pnpm, Docker, uv) are installed, their versions, and what each is needed for. Installs nothing.
spec-implement
Step 5 of the Vibe-Spec workflow. Promote a phase plan to detailed, implement it following the vibe-spec references, then update the docs so the spec reflects reality.
spec-refine
Step 2 of the Vibe-Spec workflow. Critique the V0 spec, fill gaps with clarifying questions, then promote it to a V1 spec that maps each piece of functionality to concrete stack tools using the vibe-spec references.