watch

watch is a skill for Claude Code from Kostakurta8/roundtable. It costs 42 tokens per session (260 once invoked), scanned A, original, MIT.

A local, read-only browser view of Claude Code sessions, showing subagents as people in a timeline. It reads session data from the machine and serves the view on localhost, meaning it is available only on that computer.

In plain words
What is it for?
Use it to watch the current or recent Claude Code session, see when subagents work, and review their activity without changing the sessions.
Why use it?
It removes the need to follow several agent sessions from text transcripts alone. The timeline can be rewound to inspect what happened during a run.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the roundtable plugin — 3 skills shipped together

Good fit Use it to watch the current or recent Claude Code session, see when subagents work, and review their activity without changing the sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kostakurta8/roundtable/watch
Install

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.

Any agent
npx skills add Kostakurta8/roundtable --skill watch
Clone the repo
git clone --depth 1 https://github.com/Kostakurta8/roundtable

Made for: Claude Code.

Or install roundtable, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/kostakurta8/roundtable/watch/github.svg)](https://agentmods.dev/skills/kostakurta8/roundtable/watch)
Your own site
<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.

agentmods 80×15 button for watch

Your own site · 80×15
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 96aa4e09f590, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

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.

plugin/skills/watch/SKILL.md · 23 lines

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.

Changes

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.

  1. 6d ago First seen · 23 lines · 42 tokens per session scan A 96aa4e09f590

Subscribe to this mod's changes

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.

Related

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.

wshobson/agents · 51 tokens

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.

shobcoder/shob · 38 tokens

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.

open-octo/octo-agent · 139 tokens

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…

ericrisco/rsc-harness · 76 tokens

qa-testing-playwright

Builds and debugs Playwright E2E suites. Use when authoring browser tests, fixing flakes, or hardening Playwright CI and locator strategy.

vasilyu1983/AI-Agents-public · 37 tokens

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.

awss1i/assay · 49 tokens