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 alexeyshishin/as-skill --skill content-tg-postgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/content-tg-post)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/content-tg-post"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/content-tg-post/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/alexeyshishin/as-skill/content-tg-post"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/content-tg-post.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 | $0.00076 | $0.00907 |
| Opus 5 | $0.00038 | $0.00453 |
| Sonnet 5 | $0.00015 | $0.00181 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
content-tg-post 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
content-tg-post — Telegram channel post
Goal: take an idea or raw text and turn it into one Telegram post that people want to read to the end.
Before starting, read:
~/.claude/rules/content-voice.md— authorial voice (informal "you," not Wikipedia)~/.claude/rules/content-formatting.md— the Telegram section
Step 1. Understand the material
Ask (or pull from context):
- the source: an idea in one phrase, a note from Obsidian, a draft, bullet points
- the channel's theme (if not already known): technical, personal, mixed
- the post format: a thesis / a breakdown / a personal story / an incident post-mortem / a brief how-to
If there isn't enough material for a post — stop and ask for specifics: "there isn't enough for a post, I need a real-world example or some numbers."
Step 2. Find the thesis
One post = one thesis. Ask yourself:
- what do I want the reader to walk away with?
- if they only read the first sentence, will they get the main point?
Formulate the thesis in one phrase. This is the post's first line.
Step 3. Build the structure
Standard structure for a 500-1500 character post:
<Hook / thesis — 1 sentence>
<Context or expansion of the thesis — 2-4 sentences>
<Specifics: an example, a number, code, a story — mandatory>
<Implication / conclusion / question — 1-2 sentences, or none at all>
Each block is a separate paragraph, separated by a blank line.
Step 4. Write it
Applying content-voice.md:
- no "dear readers" and no "represents"
- zero AI clichés ("let's dive in," "in this article")
- specifics > generalizations
- short sentences, short paragraphs
Applying content-formatting.md:
- technical terms in
backticks - code blocks with a language tag
- no
#headings — Telegram doesn't render them - MarkdownV2 escape characters (or use HTML formatting if the channel supports it)
Step 5. Self-check
Before showing it to the user:
- length — within the 500-1500 range? If longer — cut it. If shorter — maybe it's a tweet, not a post.
- thesis in the first line — if you remove the first 1-3 sentences, is meaning lost? If not — cut the intro.
- specifics — is there at least one example / number / command / link?
- personality — could anyone have written this? If so — add a personal observation.
- ending — does it have one at all? Or does the text just cut off? Either is fine, as long as it's not "thus."
What ships with it
1 file 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 · 94 lines · 76 tokens per session scan A 62e223501295
content-tg-post is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 21d ago), licensed MIT. It adds 76 tokens to every session and 907 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
loop-engineering
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
obsidian
Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.1, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use…
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
graph-engineering
Use when a workflow has explicit data dependencies, independently executable branches, typed joins, or node-local recovery needs that justify a bounded static dependency graph.
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.
wiki-ingest
Use when a PDF, URL, transcript, clipping, or raw note must become source-grounded, linked, governed knowledge in an Obsidian vault.