Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sh0tn1k/telegram-ads/plugin install 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/telegram-ads-watcher-runtime-enablement)<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-runtime-enablement"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-runtime-enablement/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/telegram-ads-watcher-runtime-enablement"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-runtime-enablement.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 | $0.00234 | $0.09030 |
| Opus 5 | $0.00117 | $0.04515 |
| Sonnet 5 | $0.00047 | $0.01806 |
| Haiku 4.5 | $0.00023 | $0.00903 |
Grade A, and why
telegram-ads-watcher-runtime-enablement 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 9d 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 — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable the in-process Telegram Ads watcher runtime
A class of work: the operator has accepted the V2.0 → V2.5 → V2.6 → V2.7 code drops (all committed locally, no push) and now wants to flip the runtime flags so the in-process watcher actually runs inside the hermes-gateway-default.service. The flags in question:
HERMES_ADS_WATCHER_ENABLED=1— gates the V1 in-process daemon, the V2.6 wiring, the V2.7 production.py hook, and the V2.7 production_adapter. (Lives in three callers — see Pitfall 1.)HERMES_ADS_WATCHER_INTERVAL_SECONDS=600— V1 poll interval.HERMES_ADS_WATCHER_REPORTS_ENABLED=1— gates the V2.7 report_router (12 categories).
The art of this work is not flipping flags. The art is discovering that the flags are already applied, refusing to restart, and verifying the live state with read-only commands.
When to use
- the operator hands you a runtime enablement approval that names
HERMES_ADS_WATCHER_ENABLED,HERMES_ADS_WATCHER_INTERVAL_SECONDS,HERMES_ADS_WATCHER_REPORTS_ENABLEDand asks you to "enable runtime flags for hermes-gateway-default.service". - The approval says "no push, no real Ads action, no Ads mutation, no synthetic Telegram message, no secrets printed, no standalone daemon, no deepseek/Xvfb/KC changes" — i.e. a read-only verification mission.
- The approval conditionally allows a restart ("If unit/env changed: daemon-reload; restart") and the operator often adds a "не делай рестарт" override.
- the operator hands you a
AR-ADS-WATCHER-NEXT-TICK-VERIFY-Napproval to confirm the first post-baseline tick after a V2.8+ restart completes without the 60.04sTimeoutErrorregression — see Pitfall 9.
When NOT to use
- The work is installing the watcher package →
install-hermes-telegram-ads-watcher. - The work is designing a new watcher layer (V3, autonomy
envelope changes, new event types) →
telegram-ads-watcher-event-loop-design. - The work is diagnosing a runtime symptom (watcher stuck, no
events, login_required spam) →
diagnose-hermes-internals+ references/v1-known-issues.md. - The work is a real Ads action (create, edit, change_cpm) →
operate-telegram-ads+ approval-gated path.
What ships with it
6 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.
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.
- 9d ago First seen · 738 lines · 234 tokens per session scan A 6047406893a5
telegram-ads-watcher-runtime-enablement is a skill published in the GitHub repository sh0tn1k/telegram-ads (0 stars, last pushed 8d ago), licensed MIT. It adds 234 tokens to every session and 9,030 once invoked, about $0.0012 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…