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 skills/vendelieu/telegram-bot/add-wizard-stepnpx skills add vendelieu/telegram-bot --skill add-wizard-stepgit clone --depth 1 https://github.com/vendelieu/telegram-botWrote 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/vendelieu/telegram-bot/add-wizard-step)<a href="https://agentmods.dev/skills/vendelieu/telegram-bot/add-wizard-step"><img src="https://agentmods.dev/badge/skills/vendelieu/telegram-bot/add-wizard-step.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 | $0.00037 | $0.00636 |
| Opus 5 | $0.00018 | $0.00318 |
| Sonnet 5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
add-wizard-step 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Wizard Step
Structure
Extend WizardStep. Override onEntry (required) and optionally validate, store, onRetry.
object NameStep : WizardStep(isInitial = true) {
override suspend fun onEntry(ctx: WizardContext) {
message("What's your name?").send(ctx.user, ctx.bot)
}
override suspend fun validate(ctx: WizardContext): Transition {
val text = (ctx.update as? MessageUpdate)?.message?.text ?: return Transition.Retry()
return if (text.isNotBlank()) Transition.Next else Transition.Retry("Invalid")
}
override suspend fun store(ctx: WizardContext): String? =
(ctx.update as? MessageUpdate)?.message?.text
}
Lifecycle Methods
| Method | Required | Purpose |
|---|---|---|
onEntry(ctx) |
Yes | Called when entering step. Send prompts, set keyboards. |
validate(ctx) |
No | Return Transition based on input. Default: Transition.Next |
store(ctx) |
No | Return value to persist. Type must match a state manager. Default: null |
onRetry(ctx, reason) |
No | Called when validation returns Transition.Retry. Default: no-op |
Transitions
| Transition | Effect |
|---|---|
Transition.Next |
Move to next step in sequence |
Transition.JumpTo(Step::class) |
Jump to specific step |
Transition.Retry() or Transition.Retry("reason") |
Stay on step; onRetry is called |
Transition.Finish |
End wizard |
WizardContext
ctx.user,ctx.update,ctx.botctx.getState(Step::class),ctx.setState(Step::class, value),ctx.delState(Step::class)— KSP generates type-safe accessors per step
Step ID
Override id if needed: override val id: String = "custom_id". Default: fully qualified class name.
Initial Step
Set isInitial = true on exactly one step. That step runs when the wizard starts.
Related Skills
- build-wizard-flow — Full wizard flow overview
- add-wizard-handler — Configure @WizardHandler (trigger, scope, state managers)
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 · 67 lines · 37 tokens per session scan A e405ef540513
add-wizard-step is a skill published in the GitHub repository vendelieu/telegram-bot (248 stars, last pushed 9d ago), licensed Apache-2.0. It adds 37 tokens to every session and 636 once invoked, about $0.0002 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.
Other skills, from other repositories
headless-bot
Nested swiss-knife reference for creating and operating a headless LingTai bot project without opening the TUI. Start from lingtai-tui spawn, then apply the relevant addon/MCP wiring, keep secrets in sidecar files, copy preset policy by referencing existing presets instead of copying preset JSON files, refresh or…
telegram
Multi-bot Telegram bridge — routes messages between Telegram and Claude tmux sessions.
telegram-search-cli
Operate the Telegram Search CLI through an authorized local profile. Use when an agent needs to discover Telegram chats, read bounded remote messages, explicitly synchronize history with user-approved Telegram Takeout, query/search/contextualize persisted messages, compute statistics, export deterministic JSONL, or…
c-telegram
Bidirectional Telegram bridge — talk to Claude from your phone. Built into OpenPaw.
telegram-bot
Telegram bot development - chatbots, notifications, AI assistants, and group automation.
configure
Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.