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 Kostakurta8/roundtable --skill watchgit clone --depth 1 https://github.com/Kostakurta8/roundtableWrote 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/kostakurta8/roundtable/watch)<a href="https://agentmods.dev/skills/kostakurta8/roundtable/watch"><img src="https://agentmods.dev/badge/skills/kostakurta8/roundtable/watch/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/kostakurta8/roundtable/watch"><img src="https://agentmods.dev/badge/skills/kostakurta8/roundtable/watch.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 | $0.00042 | $0.00260 |
| Opus 5.5 | $0.00017 | $0.00104 |
| Sonnet 5.5 | $0.00008 | $0.00052 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
watch 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 6d 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.
What it actually says
Start the Roundtable observer for the user.
Run this with the Bash tool, in the background (run_in_background: true) — it is a server and does not exit on its own:
npx -y https://github.com/Kostakurta8/roundtable/releases/latest/download/roundtable.tgz
It serves the office on http://localhost:7411 and opens the browser itself. Wait a few seconds, read its output once, and tell the user:
- the address it printed, and that the tab opens on the most recent session — this one;
- that it only reads
~/.claude, binds to localhost, and makes no outbound connection; - that it keeps running in the background until they stop it or end the session.
If the output says port 7411 is already in use, Roundtable is already running: tell them to open http://localhost:7411 and do not start a second copy.
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.
- 6d ago First seen · 23 lines · 42 tokens per session scan A 96aa4e09f590
watch is a skill published in the GitHub repository Kostakurta8/roundtable (21 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 260 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
web-scraper
Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
qa-testing-playwright
Builds and debugs Playwright E2E suites. Use when authoring browser tests, fixing flakes, or hardening Playwright CI and locator strategy.
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.