radin-stats

radin-stats is a skill for Claude Code, Codex from shortcuts/radin. It costs 56 tokens per session (493 once invoked), scanned A, original, MIT.

A report that displays statistics from installed companion tools next to one another. It keeps different measures separate, such as actual session savings, published benchmark results, and per-repository records.

In plain words
What is it for?
Use it to run available statistics or gain commands, show their outputs, and review token savings, benchmark results, or deferred-work records.
Why use it?
It gives one overview without adding together figures that measure different things and would produce a misleading total.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the radin plugin — 9 skills, 1 agent shipped together

Good fit Use it to run available statistics or gain commands, show their outputs, and review token savings, benchmark results, or deferred-work records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shortcuts/radin/radin-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 shortcuts/radin --skill radin-stats
Clone the repo
git clone --depth 1 https://github.com/shortcuts/radin

Made for: Claude Code, Codex.

Or install radin, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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 radin-stats

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/shortcuts/radin/radin-stats"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 493 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 $0.00056 $0.00493
Opus 5 $0.00028 $0.00246
Sonnet 5 $0.00011 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured today against content hash cf40a194d212, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

radin-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 today.

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.

skills/radin-stats/SKILL.md · 43 lines

What it actually says

Stats Roundup

Print each installed tool's own stats or gain command, back to back. Do not compute a merged total: the numbers use incompatible units -- real per-session tokens, static benchmark medians, and a counted per-repo ledger. A sum would misrepresent all three. Display each output as-is.

Step 1: Invoke each available source

Run whichever sources are installed, checking with command -v or a skill lookup. Skip a missing source without printing anything, and never treat it as an error.

  • /caveman:caveman-stats -- real per-session token usage and savings, read from the session log itself.
  • /ponytail:ponytail-gain -- ponytail's published benchmark scoreboard (medians across 5 tasks, 3 models). Not this session, and not this repo.
  • /ponytail:ponytail-debt -- ponytail's real per-repo ledger of deferred shortcuts, if the repo has one.
  • rtk gain -- rtk's real token-savings ledger (command -v rtk; pass -p to scope it to the current project).

Any other installed tool with its own stats or gain command belongs in this list too. Add it here rather than building a separate skill.

If a source finds nothing to report, treat that as a normal empty result: one quick check, then move on. Do not keep searching for entries that are not there. This output is informative only, so it does not need to be exact.

Step 2: Display, don't merge

Print each tool's output under its own heading, in the order above. Label which numbers are really measured (caveman-stats, ponytail-debt, rtk gain) and which come from a fixed benchmark (ponytail-gain), so the user does not mistake one for the other. Print no combined total row.

Files

What ships with it

1 file 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.

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. today Changed · +15 lines cf40a194d212
  2. 9d ago First seen · 28 lines · 56 tokens per session scan A d170f8b536fb

Subscribe to this mod's changes

radin-stats is a skill published in the GitHub repository shortcuts/radin (5 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 493 once invoked, about $0.0003 per session on Opus 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.