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 sh0tn1k/telegram-ads --skill create-telegram-ads-campaign-workflowgit clone --depth 1 https://github.com/sh0tn1k/telegram-adsWrote 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/sh0tn1k/telegram-ads/create-telegram-ads-campaign-workflow)<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/create-telegram-ads-campaign-workflow"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/create-telegram-ads-campaign-workflow/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/sh0tn1k/telegram-ads/create-telegram-ads-campaign-workflow"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/create-telegram-ads-campaign-workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.06052 |
| Opus 5 | $0.00042 | $0.03026 |
| Sonnet 5 | $0.00017 | $0.01210 |
| Haiku 4.5 | $0.00008 | $0.00605 |
Grade A, and why
create-telegram-ads-campaign-workflow 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 7d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Telegram Ads Campaign Workflow
Operational end-to-end procedure for creating a Telegram Ads campaign. This skill covers only the operational sequence — the actual creative / targeting / CPM / budget choices come from prepare-and-manage-tg-ads (strategy layer). The skill's job is to drive the tools in the correct order, gate on validation, present an approval request, and only then submit.
When to Use
- the operator asks to "create a new Telegram Ads campaign".
- A draft is already shaped (title, text, promote_url, cpm, budget, target_type, targets) and ready to go to moderation.
- A new variant of an existing ad is being prepared via
duplicate_ad/create_similar_draft.
When NOT to Use
- The draft itself is not yet shaped — start with
prepare-and-manage-tg-adsfor creative / targeting / CPM / budget. - Editing a live ad — that uses
edit_adand re-triggers moderation; this skill is for new ads. - Pausing / resuming / changing CPM / budget on an existing ad — separate operational skills.
Operating Discipline (mandatory)
This skill submits to moderation and spends money on activation. It is governed by ~/.hermes/shared/TELEGRAM_ADS_TOOL_CONTRACT.md §0 (Operating Discipline):
- No manual browser fallback during this workflow. All steps go through typed Telegram Ads tools.
- No
ps/pkill/gateway restart without explicit operator approval. - Confirmation flow is mandatory: never call
create_ad(or any other CONFIRM_REQUIRED action) without first getting an approval from the operator using the structured format in §"Approval Request Format" below. confirmation_idis single-use, fingerprint-bound, TTL 300s. Reuse is rejected; modify-any-byte in the draft between prepare and apply also rejects. Apply must happen in the next tool call after prepare.initial_activedoes NOT skip moderation. It only controls what happens after Telegram approves the ad: withinitial_active: true, the ad begins serving (and spending) immediately on approval; withinitial_active: false(the default), the ad stays paused after approval and must be explicitly started viastart_ad. The moderation step happens either way. Default for any test / review campaign:initial_active: false. Only setinitial_active: truefor production campaigns that the operator has explicitly approved to begin spending on approval.
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.
- 7d ago Changed · +23 lines d5a2a5ebeef4
- 10d ago First seen · 314 lines · 84 tokens per session scan A 075ea168b572
create-telegram-ads-campaign-workflow is a skill published in the GitHub repository sh0tn1k/telegram-ads (0 stars, last pushed 10d ago), licensed MIT. It adds 84 tokens to every session and 6,052 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…