A command that reports how often work was sent to different models and how many tokens those agents actually used. It can limit the report to a number of days, an earlier time window, or sessions using one model.

Use it to inspect dispatch counts, token volume, per-model routing, and the share of work handled below the session’s model tier.

It helps explain model usage and whether cheaper models handled part of the work. This makes unusual routing patterns or unexpectedly expensive sessions easier to spot.

stats — Command for coding agents by AqueGen: A command that reports how often work was sent…

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.

agentmods

npx agentmods add commands/aquegen/model-routing/stats

Clone the repo

git clone --depth 1 https://github.com/AqueGen/model-routing

Or install model-routing, the plugin that ships this one along with the rest of its 1 skill, 1 command, 7 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/aquegen/model-routing/stats.svg)](https://agentmods.dev/commands/aquegen/model-routing/stats)

Your own site

<a href="https://agentmods.dev/commands/aquegen/model-routing/stats"><img src="https://agentmods.dev/badge/commands/aquegen/model-routing/stats.svg" alt="Measured on agentmods" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 364 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00058	$0.00364
Opus 5	$0.00029	$0.00182
Sonnet 5	$0.00012	$0.00073
Haiku 4.5	$0.00006	$0.00036

Measured 3d ago against content hash 29f51fce9ccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

commands/stats.md · 27 lines

What it actually says

Dispatch report:

!node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch-counter.mjs" report $ARGUMENTS 2>&1 || echo "model-routing: stats script failed - node 18+ must be on PATH"

Real token volume (from subagent transcripts):

!node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch-counter.mjs" tokens $ARGUMENTS 2>&1 || echo "model-routing: tokens script failed - node 18+ must be on PATH"

If either block above is empty or shows a shell error (not a script message - the script itself always explains empty data in words), the embedded shell run failed silently. In that case run the two commands yourself through whatever shell tool works in this session (node <plugin>/hooks/dispatch-counter.mjs report and ... tokens) and present those results instead.

Present both reports above to the user as-is in code blocks, then add 2-3 short sentences of interpretation: what share of dispatches and of token volume stayed below the session model, how the per-session-model split compares (e.g. fable sessions routing down more than opus sessions), and anything that looks off (e.g. many subagents running AT the session tier). Do not re-run the commands, no extra tables, no dollar estimates.

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.

3d ago First seen · 27 lines · 0 tokens per session scan A 29f51fce9ccd

Subscribe to this mod's changes

stats is a command published in the GitHub repository AqueGen/model-routing (3 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 364 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.

Analytics and metrics Cost Optimization claude claude-code claude-code-plugin reasoning-effort token-economy

stats

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

greet

hello

costguard-audit

costguard-fix

doctor

benchmark