# Radin Stats

> |

- **Type:** Skill
- **Install:** `agentstack add skill-shortcuts-radin-radin-stats`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [shortcuts](https://agentstack.voostack.com/s/shortcuts)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [shortcuts](https://github.com/shortcuts)
- **Source:** https://github.com/shortcuts/radin/tree/main/skills/radin-stats

## Install

```sh
agentstack add skill-shortcuts-radin-radin-stats
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Stats Roundup

Surface each installed companion tool's own stats/gain command, back to back.
No merged total: the numbers below use incompatible units (real per-session
tokens, static benchmark medians, a counted per-repo ledger) — summing them
would misrepresent all three, so display each as-is instead.

## Step 1: Invoke each available source

Run whichever of these are installed (`command -v` / skill lookup — skip
silently if missing, don't error):

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

Any other installed tool with its own `stats`/`gain` command belongs here
too — add it to this list, don't build a separate skill.

If a source (e.g. `caveman-stats`) finds nothing to report, treat that as a
normal empty result — one quick check, then move on. Don't keep searching
for entries that aren't there. This is informative only, not exact/precise
required.

## Step 2: Display, don't merge

Print each tool's output under its own heading, in the order above. Label
which are real-measured (caveman-stats, ponytail-debt, rtk gain) vs.
fixed-benchmark (ponytail-gain) so the user doesn't mistake one for the
other. Do not add a combined total row.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [shortcuts](https://github.com/shortcuts)
- **Source:** [shortcuts/radin](https://github.com/shortcuts/radin)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-shortcuts-radin-radin-stats
- Seller: https://agentstack.voostack.com/s/shortcuts
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.