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 telegram-ads-watcher-event-loop-designgit 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/telegram-ads-watcher-event-loop-design)<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-event-loop-design"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-event-loop-design/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-event-loop-design"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/telegram-ads-watcher-event-loop-design.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 | $0.14601 |
| Opus 5 | $0.00117 | $0.07301 |
| Sonnet 5 | $0.00047 | $0.02920 |
| Haiku 4.5 | $0.00023 | $0.01460 |
Grade A, and why
telegram-ads-watcher-event-loop-design scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
20. `_run_tick_once` source contains no `*_daemon` entrypoint, no `while True`, no `subprocess.Popen`. How it starts
The opening of the file, as written. The whole thing — 1,137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design a Telegram Ads post-action watcher event loop
A class of work: the operator wants a new Hermes-facing layer on top of the
already-installed hermes_telegram_ads.watcher package. The new layer:
- Wraps the existing
WatchSpec/WatcherEvent/recipeswith Hermes-only fields (expected_outcome,max_duration_seconds,autonomy_envelope,safe_summary,requires_approval,report_category). - Models a bounded autonomy envelope that names which fix types an
approval grants, with deny-all defaults and a structured
MutationBlockedErrorfor every refusal path. - Builds a pure mini-report formatter that produces short secret-redacted summaries — with report routing off by default until the operator approves it separately.
- Ships a thorough pytest suite that pins all closed sets, asserts no mutation path exists in V2, and exercises every deny-by-default branch of the guard.
When to use
- the operator says "event loop V2/V3", "post-action watcher", "autonomy envelope", "bounded remediation", "mini reports to the operator", "mutation guard for Telegram Ads", or hands you a phased approval that lists "event model + watchspec + report formatter + autonomy envelope + tests, no mutation execution, no production report sending".
- the operator wants a new module/package in
gateway/(e.g.gateway/ads_watcher_v2/) that extends but does not duplicate the externalhermes_telegram_ads.watcherpackage. - The work is greenfield feature design with explicit "do not start a daemon / do not send Telegram messages / do not change CPM" guardrails.
When NOT to use
- The work is installing or upgrading the
hermes_telegram-ads-manager-toolpackage → useinstall-hermes-telegram-ads-watcher. - The work is patching an existing Hermes module (Sleep Engine,
memory lifecycle, ontology, etc.) → use
audit-and-patch-hermes-module. - The work is adding a CLI subcommand to expose watcher state →
use
add-hermes-cli-observability-command. - The work is building a new domain stack (typed models → store →
service → dispatcher) → use
hermes-domain-layer-development. (V2 is a thin wrapper layer, NOT a full stack.) - The work is diagnosing a runtime symptom (watcher stuck, no
events, login_required spam) → use
diagnose-hermes-internals+install-hermes-telegram-ads-watcher/references/login-state-scheduler-gate.md.
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.
- 11d ago First seen · 1,137 lines · 234 tokens per session scan A 5cb4d5de1a14
telegram-ads-watcher-event-loop-design is a skill published in the GitHub repository sh0tn1k/telegram-ads (0 stars, last pushed 10d ago), licensed MIT. It adds 234 tokens to every session and 14,601 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…