council-stats

council-stats is a command for Claude Code from sergei-aronsen/claude-code-toolkit. It costs 18 tokens per session (535 once invoked), scanned A, original, MIT.

A command that displays usage, token counts, and costs recorded for Supreme Council calls, using a local log without API requests.

In plain words
What is it for?
Use `/council-stats` for daily, weekly, monthly, total, date-range, or CSV reports.
Why use it?
It makes it easier to find unexpected spending, compare usage, and prepare billing summaries.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: reads .claude/ paths; positional $N argument; mentions Codex.

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/sergei-aronsen/claude-code-toolkit/council-stats
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

Made for: Claude Code.

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 council-stats

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/council-stats.svg)](https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/council-stats)
Your own site
<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/council-stats"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/council-stats.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00535
Opus 5 $0.00009 $0.00267
Sonnet 5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00053

Measured 6d ago against content hash 53612487bbf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

council-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 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.

commands/council-stats.md · 53 lines

What it actually says

/council-stats

Render Council token usage and cost from the local log (~/.claude/council/usage.jsonl). No API calls — works offline.

Purpose

Show how many Council calls have been made, broken down by provider, model, and mode, with token counts and dollar cost. Use it to spot runaway spend, verify CLI mode is actually saving money, or pull a CSV for billing reconciliation.

When to Use

Situation Use /council-stats
Wonder where today's tokens went --day
Monthly cost report --month --csv
Audit a specific date range --since 2026-04-01 --until 2026-04-30
Validate that CLI mode is free --total (CLI rows show $0.0000)

Usage

When the user types /council-stats (or any of the period variants below), run the corresponding brain stats invocation and present the output verbatim.

User asks for Command
Today / last 24h brain stats --day
This week brain stats --week
This month brain stats --month
All time (default) brain stats --total
Range brain stats --since 2026-04-01 --until 2026-04-30
Machine-readable append --csv to any of the above

The output is grouped by (provider, model, mode) and totals tokens + cost in USD. Cost comes from ~/.claude/council/pricing.json overlaid on the built-in DEFAULT_PRICING table. CLI calls (Gemini CLI, Codex CLI) are priced at $0 per token because subscription covers them; their token counts are estimated (chars / 4) and marked with estimated: true per record.

Notes

  • The log is append-only and never sent off-machine. Delete it with rm ~/.claude/council/usage.jsonl if you want to reset history.
  • Update ~/.claude/council/pricing.json when provider rates change. Local edits are preserved on toolkit update via the .upstream-new.json sidecar pattern.
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 · 53 lines · 18 tokens per session scan A 53612487bbf7

Subscribe to this mod's changes

council-stats is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 20d ago), licensed MIT. It adds 18 tokens to every session and 535 once invoked, about $0.0001 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.