Borrowing it
Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/telegram-bot-test/SKILL.mdgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/telegram-bot-test)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/telegram-bot-test"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/telegram-bot-test.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.00899 |
| Opus 5 | $0.00051 | $0.00449 |
| Sonnet 5 | $0.00020 | $0.00180 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade B, and why
telegram-bot-test scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -15 .claude/chat/bot.log | grep -E "\[Process\]|\[Recall\]|Runtime" How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Bot E2E Test
Test the The Homie bot by chatting with it on Telegram Web via agent-browser.
Prerequisites
- Bot running:
cd .claude/chat && bash run_chat.sh - agent-browser daemon running (start if not):
node "$(npm root -g)/agent-browser/dist/daemon.js" & - Telegram Web logged in (user should already be logged in)
Workflow
1. Open Telegram Web and navigate to YourAgent bot
npx agent-browser open https://web.telegram.org/a/
npx agent-browser snapshot -i -c # find YourAgent chat link
npx agent-browser click @eN # click YourAgent chat
2. Send a message (type in the browser input)
npx agent-browser snapshot -i -c -s "[contenteditable]" # find input ref
npx agent-browser click @e1 # focus input
npx agent-browser keyboard type "your test message here" # type message
npx agent-browser press Enter # send
IMPORTANT: Use keyboard type (not type @ref). Telegram Web uses contenteditable divs — type @ref can timeout. keyboard type sends real keystrokes.
3. Wait for response and verify
sleep 10 # wait for bot to respond
npx agent-browser screenshot /path/to/screenshot.png # visual check
Then check bot.log for cognitive events:
tail -15 .claude/chat/bot.log | grep -E "\[Process\]|\[Recall\]|Runtime"
4. Evaluate pass/fail
- PASS: Bot responded with relevant content (visible in screenshot) AND expected log events appeared
- FAIL: Bot returned error message, no response, or wrong cognitive mode detected
Test Cases
Run each test by sending /new first (reset session), then the test message.
Process Detection (Move 3)
| Mode | Message to Send | Expected in bot.log |
|---|---|---|
| Planning | "how should we approach the brand fleet SEO?" | [Process].*new=planning |
| Monitoring | "check on the server health" | [Process].*new=monitoring |
| Learning | "remember that the teller cert expires next week" | [Process].*new=learning |
| Execution | "build the weekly synthesis report" | [Process].*new=execution |
| Default | "what's up with the recovery campaigns?" | No [Process] line (stays default) |
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.
- 4d ago First seen · 88 lines · 101 tokens per session scan B 77fa786378d6
telegram-bot-test is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 899 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
e2e-setup
Set up Playwright e2e automation tailored to this team and app. Probes the running app (auth mechanism, API surface, spec availability), interviews with recommendations instead of open questions, scaffolds the playwright/ folder, and records every decision in playwright/AUTOMATION.md for the other e2e skills to read.…
verify-fix
Re-test a bug fix after a developer resolves it. Pulls the original bug from Jira, re-executes the repro steps in the browser, checks for regressions, and updates the bug status. The final step in the SDT workflow before a ticket moves to Done. Use when: "verify fix", "retest", "is this fixed?", "check BUG-123"…
playwright-skill
Complete browser automation with Playwright. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, and automate browser tasks. Use when the user wants browser-based testing or scripted web automation.
webapp-testing
Toolkit for testing web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing screenshots, or viewing browser logs.
webapp-testing
Automated webapp testing with Playwright. Server management, UI testing, visual debugging, and reconnaissance-first approach.
webapp-testing
Playwright-driven testing of local web apps.