configure

configure is a command for Claude Code from q1343135559/ClaudeMeter. It costs 9 tokens per session (1,541 once invoked), scanned A, original, MIT.

A guided configuration command for ClaudeMeter, a status-line display for Claude usage and session information.

In plain words
What is it for?
Use it to change the displayed status-line sections, filter models, set bar width, configure warning thresholds, rename labels, adjust path depth, and set the staleness warning.
Why use it?
It helps adjust which usage windows, model details, paths, costs, labels, and warning colors appear in the terminal.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Part of the claudemeter plugin — 2 commands shipped together

Good fit Use it to change the displayed status-line sections, filter models, set bar width, configure warning thresholds, rename labels, adjust path depth, and set the staleness warning.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/q1343135559/claudemeter/configure
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.

Clone the repo
git clone --depth 1 https://github.com/q1343135559/ClaudeMeter

Made for: Claude Code.

Or install claudemeter, the plugin that ships this one along with the rest of its 2 commands.

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 configure

README.md
[![agentmods](https://agentmods.dev/badge/commands/q1343135559/claudemeter/configure.svg)](https://agentmods.dev/commands/q1343135559/claudemeter/configure)
Your own site
<a href="https://agentmods.dev/commands/q1343135559/claudemeter/configure"><img src="https://agentmods.dev/badge/commands/q1343135559/claudemeter/configure.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 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 $0.00009 $0.01541
Opus 5 $0.00005 $0.00771
Sonnet 5 $0.00002 $0.00308
Haiku 4.5 $0.00001 $0.00154

Measured 3d ago against content hash f29120f5d729, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

configure 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.

plugin/commands/configure.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeMeter Configure

Walk the user through adjusting ClaudeMeter's display configuration. Talk to them in whatever language they are using.

1. Read the current configuration

The config file lives at {CLAUDE_CONFIG_DIR:-~/.claude}/claudemeter/config.json.

CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
cat "$CONFIG_DIR/claudemeter/config.json" 2>/dev/null || echo '{}'

A missing file is normal and means every value is at its default.

2. Ask what they want to change

Use AskUserQuestion, at most four questions at a time. Worthwhile directions:

  • Which segments to show: line 1 (model / path / branch / cost), the context bar, the 5-hour window, the weekly window, per-model windows
  • Only certain models: scopedFilter — e.g. ["Fable"] shows only Fable's weekly window
  • Bar width: auto (adapts to terminal width), a fixed cell count, or 0 (percentages only)
  • When bars change colour: thresholds.warning (default 50, turns yellow) and thresholds.critical (default 80, turns light red)
  • Labels: rename CTX / 5H / WEEK
  • Path depth: pathLevels
  • Staleness threshold: staleWarnMs
  • Background refresh: autoRefresh — whether the statusline may start claude -p /usage in the background (at most every five minutes) so per-model windows such as FABLE keep updating

Show the values currently in effect before asking.

3. Write the configuration back

Change only the keys the user asked about; preserve everything else. Some advanced keys (colors, thresholds, staleMaxMs, maxWidth) are not part of this guided flow, but if the user has set them by hand they must survive the write.

CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
mkdir -p "$CONFIG_DIR/claudemeter"

Read the existing file, mutate that object, and write it back. Do not rebuild it from scratch.

4. Verify

CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
COLUMNS=120 node "$CONFIG_DIR/claudemeter/launcher.mjs" --demo

Read the full file on GitHub · 123 lines

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. 3d ago Changed · +8 lines f29120f5d729
  2. 7d ago First seen · 115 lines · 9 tokens per session scan A 925bc0726279

Subscribe to this mod's changes

configure is a command published in the GitHub repository q1343135559/ClaudeMeter (1 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 1,541 once invoked, about $0.0000 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.