Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add q1343135559/ClaudeMeter/plugin install claudemeterWrote 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.
[](https://agentmods.dev/commands/q1343135559/claudemeter/setup)<a href="https://agentmods.dev/commands/q1343135559/claudemeter/setup"><img src="https://agentmods.dev/badge/commands/q1343135559/claudemeter/setup/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.
<a href="https://agentmods.dev/commands/q1343135559/claudemeter/setup"><img src="https://agentmods.dev/badge/commands/q1343135559/claudemeter/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00009 | $0.01630 |
| Opus 5.5 | $0.00004 | $0.00652 |
| Sonnet 5.5 | $0.00002 | $0.00326 |
| Haiku 4.5 | $0.00001 | $0.00163 |
Grade A, and why
setup 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClaudeMeter Setup
Install ClaudeMeter as the user's statusline. Follow the steps in order — each one exists for a reason that is stated inline. Talk to the user in whatever language they are using.
1. Locate the runtime and the plugin
node -e "console.log(process.execPath)"
Take the absolute path to Node. Never write a bare node into settings.json: the statusline
runs as a child process of Claude Code, whose PATH may not include an nvm- or Homebrew-managed
Node. A bare command fails silently on many machines — the statusline simply never appears, with
no error anywhere.
If that command fails, Node is not on PATH. Tell the user ClaudeMeter needs Node.js 18 or later,
then stop.
The plugin root is ${CLAUDE_PLUGIN_ROOT}; the launcher source is at
${CLAUDE_PLUGIN_ROOT}/bin/launcher.mjs.
2. Install the launcher at a stable path
CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
mkdir -p "$CONFIG_DIR/claudemeter"
cp "${CLAUDE_PLUGIN_ROOT}/bin/launcher.mjs" "$CONFIG_DIR/claudemeter/launcher.mjs"
echo "installed: $CONFIG_DIR/claudemeter/launcher.mjs"
Why the extra indirection: ${CLAUDE_PLUGIN_ROOT} is not expanded inside the statusLine
command in settings.json, and the plugin cache path contains a version number
(plugins/cache/<marketplace>/claudemeter/<version>/), so it changes on every upgrade. The
launcher resolves the highest installed version at runtime, which means plugin upgrades take
effect without re-running setup.
3. Check for and back up an existing statusline
CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
node -e "
const fs=require('fs'), p=process.argv[1];
try { const s=JSON.parse(fs.readFileSync(p,'utf8'));
console.log(JSON.stringify(s.statusLine ?? null, null, 2)); }
catch (e) { console.log('null'); }
" "$CONFIG_DIR/settings.json"
- Output is
null→ nothing configured, go straight to step 4. - Output mentions
claudemeter→ this plugin installed it before, overwrite without asking. - Anything else → the user already runs a different statusline. Show them the current value, then use AskUserQuestion to confirm the replacement. If they decline, stop and change nothing.
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.
- 1mo ago First seen · 154 lines · 9 tokens per session scan A 2b98b58fe521
setup is a command published in the GitHub repository q1343135559/ClaudeMeter (1 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,630 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
ccc-orchestrate
Run a sequential multi-agent workflow (feature, bugfix, refactor, security or custom chain) with structured handoffs, plus optional tmux and worktree workers for long-running sessions. Use when a task needs planner, implementer and reviewer stages in order.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
ralph-help
Explain Ralph Loop plugin and available commands.
ccc-rules-distill
Scan installed skills for principles that recur across them and propose them as rules, writing only what you approve. Use when skills repeat the same guidance or the rules directory has drifted from them.
environment-switching-local-cloud-ssh
The environment selector at the bottom of Claude Code switches where work executes: local for fast interactive iteration, cloud (Anthropic servers) for routines that must run with your machine off, SSH for driving a remote box like a VPS.