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 agntdev/skills --skill telegram-bot-anti-patternsgit clone --depth 1 https://github.com/agntdev/skillsWrote 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/agntdev/skills/telegram-bot-anti-patterns)<a href="https://agentmods.dev/skills/agntdev/skills/telegram-bot-anti-patterns"><img src="https://agentmods.dev/badge/skills/agntdev/skills/telegram-bot-anti-patterns/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/agntdev/skills/telegram-bot-anti-patterns"><img src="https://agentmods.dev/badge/skills/agntdev/skills/telegram-bot-anti-patterns.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 | $0.00200 | $0.01640 |
| Opus 5.5 | $0.00080 | $0.00656 |
| Sonnet 5.5 | $0.00040 | $0.00328 |
| Haiku 4.5 | $0.00020 | $0.00164 |
Grade A, and why
telegram-bot-anti-patterns 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
telegram-bot-anti-patterns Skill
The final review pass before shipping a Telegram bot — 21 anti-patterns (each one its own file under references/) plus a 21-item UX review checklist. For the rules these anti-patterns break, see telegram-bot-ux-rules. For flow patterns, see telegram-bot-flow-patterns.
Built for the agntdev pipeline. Run through the checklist in references/ux-review-checklist.md before shipping the bot. If any item is "no", the bot isn't done.
Anti-patterns index
Each entry is one file under references/. Read individually when you suspect you're doing it.
| # | Anti-pattern | Why | File |
|---|---|---|---|
| 1 | New message per dialog step | Spams chat | 01-message-per-step.md |
| 2 | Button label as a question | Buttons are actions, not queries | 02-button-as-question.md |
| 3 | Wall-of-text /start | Mobile scrolls | 03-wall-of-text-start.md |
| 4 | Emoji-only keyboards | Decoration ≠ clarity | 04-emoji-only-keyboards.md |
| 5 | Missing answerCallbackQuery() |
Spinner never stops | 05-missing-answer-callback-query.md |
| 6 | Hardcoded chat_id |
Multi-tenant fails | 06-hardcoded-chat-id.md |
| 7 | No /help command |
Users get stuck | 07-no-help-command.md |
| 8 | No empty state | New users see nothing | 08-no-empty-state.md |
| 9 | Group ambient without privacy-mode off | Telegram doesn't deliver | 09-group-ambient-without-privacy-mode.md |
| 10 | Secret-feature discovery | Users can't find features | 10-secret-feature-discovery.md |
| 11 | Edit message >48h old | "Message to edit not found" | 11-edit-message-too-old.md |
| 12 | HTML without escaping </>/& |
"Can't parse entities" 400 | 12-html-without-escaping.md |
| 13 | Non-ASCII callback_data >30 chars |
BUTTON_DATA_INVALID (64 BYTES) |
13-callback-data-bytes-vs-chars.md |
| 14 | Missing input_field_placeholder |
Users see empty input field | 14-missing-input-field-placeholder.md |
| 15 | No copy_text for IDs/codes |
Users long-press, 4 taps wasted | 15-no-copy-text-for-ids.md |
| 16 | bot.catch leaks err.message/err.stack |
Leaks internals, scares users | 16-bot-catch-leaks-stack.md |
| 17 | Edit-in-place on a message you don't own | Telegram rejects | 17-edit-in-place-not-owned.md |
| 18 | getUpdates polling without backoff |
Tight loop hammers the API | 18-polling-without-backoff.md |
| 19 | "Reply /cancel to stop" without a /cancel handler |
Dead instruction | 19-cancel-instruction-without-handler.md |
| 20 | Sending media >20MB on official API | Webhook delivery fails | 20-media-over-webhook-limit.md |
| 21 | DM a user by their Telegram ID (no invite flow) | Bot can't reach members (403) | 21-dm-user-by-id.md |
What ships with it
22 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.
- references/01-message-per-step.md 1.4 KB
- references/02-button-as-question.md 940 B
- references/03-wall-of-text-start.md 1.8 KB
- references/04-emoji-only-keyboards.md 1.4 KB
- references/05-missing-answer-callback-query.md 1.4 KB
- references/06-hardcoded-chat-id.md 1.1 KB
- references/07-no-help-command.md 1.1 KB
- references/08-no-empty-state.md 1.3 KB
- references/09-group-ambient-without-privacy-mode.md 1.4 KB
- references/10-secret-feature-discovery.md 1.4 KB
- references/11-edit-message-too-old.md 1.3 KB
- references/12-html-without-escaping.md 1.2 KB
- references/13-callback-data-bytes-vs-chars.md 1.8 KB
- references/14-missing-input-field-placeholder.md 1.4 KB
- references/15-no-copy-text-for-ids.md 1.4 KB
- references/16-bot-catch-leaks-stack.md 1.5 KB
- references/17-edit-in-place-not-owned.md 1.7 KB
- references/18-polling-without-backoff.md 1.9 KB
- references/19-cancel-instruction-without-handler.md 1.3 KB
- references/20-media-over-webhook-limit.md 1.9 KB
- references/21-dm-user-by-id.md 3.0 KB
- references/ux-review-checklist.md 3.6 KB
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.
- 2mo ago First seen · 101 lines · 200 tokens per session scan A 5a617e470141
telegram-bot-anti-patterns is a skill published in the GitHub repository agntdev/skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 200 tokens to every session and 1,640 once invoked, about $0.0008 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…