stats

stats is a skill for Claude Code from Kostakurta8/roundtable. It costs 49 tokens per session (199 once invoked), scanned A, original, MIT.

A read-only report of Claude Code transcripts stored on the machine. It measures how work was divided among subagents, their startup costs, and which hooks ran.

In plain words
What is it for?
Use it to review subagent fan-out, estimate work written by child agents, check child startup costs, and see which hooks have fired.
Why use it?
It removes the need to inspect session transcripts manually when trying to understand how agents were used. It also preserves the report's warnings about limits in the measurements.

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 review subagent fan-out, estimate work written by child agents, check child startup costs, and see which hooks have fired.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/kostakurta8/roundtable/stats/github.svg)](https://agentmods.dev/skills/kostakurta8/roundtable/stats)
Your own site
<a href="https://agentmods.dev/skills/kostakurta8/roundtable/stats"><img src="https://agentmods.dev/badge/skills/kostakurta8/roundtable/stats/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 stats

Your own site · 80×15
<a href="https://agentmods.dev/skills/kostakurta8/roundtable/stats"><img src="https://agentmods.dev/badge/skills/kostakurta8/roundtable/stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 199 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 $0.00049 $0.00199
Opus 5.5 $0.00020 $0.00080
Sonnet 5.5 $0.00010 $0.00040
Haiku 4.5 $0.00005 $0.00020

Measured 1mo ago against content hash 0e3ce3c817ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stats 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 1mo 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/stats/SKILL.md · 13 lines

What it actually says

Roundtable read every transcript under ~/.claude. Its report, exactly as printed:

!npx -y https://github.com/Kostakurta8/roundtable/releases/latest/download/roundtable.tgz --stats

Show the report to the user unchanged, in a code block. Then add at most three short observations about their numbers — which line is most unusual and what it means for how they use subagents. Keep the report's own caveats (the per-line usage over-count, hooks that fire without writing a record); do not restate them as your own findings. Do not run anything else.

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. 1mo ago First seen · 13 lines · 49 tokens per session scan A 0e3ce3c817ae

Subscribe to this mod's changes

stats is a skill published in the GitHub repository Kostakurta8/roundtable (22 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 199 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

stats compared with skills from other repositories

stats next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
statsKostakurta8/roundtableSkill221mo agoMITA49Claude Code
rote-compiletrevhud/roteSkill83d agoApache-2.0A175Claude Code, Codex
implementtrevhud/roteSkill83d agoApache-2.0A144Claude Code
servetrevhud/roteSkill83d agoApache-2.0A88Claude Code
setuptrevhud/roteSkill83d agoApache-2.0A79Claude Code
api-interface-designMohitGoyal09/AgentForgeSkill6728d agoMITA23Claude Code, Codex
exploreMohitGoyal09/AgentForgeSkill6728d agoMITA15Claude Code, Codex