Affaan Mustafa b3268fef80 fix: resolve four bug reports (#2290, #2282, #2276, #2272)
- #2290 suggest-compact: honor ECC_CONTEXT_WINDOW_TOKENS / CLAUDE_CODE_AUTO_COMPACT_WINDOW
  so 400k-window models (Opus 4.x) no longer report ~double context usage; add
  override + isolation tests in transcript-context.test.js.
- #2282 install: bare-language syntax is legacy-only by design, but the error
  now distinguishes a supported-but-wrong-mode target (gemini/codex/…) from a
  genuinely unknown one and points to --profile/--modules/--skills.
- #2276 cost-report: the command + cost-tracking skill targeted a SQLite DB no
  tracker writes. Repoint both at the real ~/.claude/metrics/costs.jsonl (JSONL,
  estimated_cost_usd), reduce cumulative-per-session snapshots to latest-per-session,
  and use node instead of sqlite3 for cross-platform support.
- #2272 gateguard: make the 'confirm no existing file' checklist item
  tool-agnostic (Glob/Grep or find/grep via Bash) so hosts without a Glob tool
  don't get a dead tool call.

Full suite 2839/2839; lint green.
2026-06-18 16:49:58 -04:00

3.8 KiB

description, argument-hint
description argument-hint
Generate a local Claude Code cost report from the ECC cost-tracker metrics log.
csv

Cost Report

Summarize local Claude Code spend by day, model, and session from the metrics log that ECC's stop:cost-tracker hook writes.

Where the data lives

The tracker appends one JSON object per session-stop to ~/.claude/metrics/costs.jsonl. Each row is a cumulative snapshot for that session, so the report takes the latest row per session_id and sums across sessions (summing every row would multiply-count).

Row schema: { timestamp, session_id, transcript_path, model, input_tokens, output_tokens, cache_write_tokens, cache_read_tokens, estimated_cost_usd }

What this command does

  1. Check that ~/.claude/metrics/costs.jsonl exists. If it does not, tell the user the tracker is not set up yet (it populates after the first session ends with the stop:cost-tracker hook enabled).
  2. Reduce rows to the latest snapshot per session and aggregate.
  3. Present a compact report, or export recent rows as CSV when the argument is csv.

node is used instead of sqlite3/jq so this works identically on macOS, Linux, and Windows.

Report

node -e '
const fs=require("fs"),os=require("os"),path=require("path");
const f=path.join(os.homedir(),".claude","metrics","costs.jsonl");
if(!fs.existsSync(f)){console.log("Cost tracker not set up: "+f+" not found. Enable the stop:cost-tracker hook and finish a session first.");process.exit(0);}
const rows=fs.readFileSync(f,"utf8").split(/\r?\n/).filter(Boolean).map(l=>{try{return JSON.parse(l)}catch{return null}}).filter(Boolean);
const bySession=new Map();
for(const r of rows){const k=r.session_id||r.transcript_path||r.timestamp;const p=bySession.get(k);if(!p||String(r.timestamp)>String(p.timestamp))bySession.set(k,r);}
const latest=[...bySession.values()];
const cost=r=>Number(r.estimated_cost_usd)||0;
const day=r=>String(r.timestamp||"").slice(0,10);
const today=new Date().toISOString().slice(0,10);
const d=new Date(Date.now()-864e5).toISOString().slice(0,10);
const sum=a=>a.reduce((s,r)=>s+cost(r),0);
const f4=n=>"$"+n.toFixed(4);
console.log("=== Cost summary ===");
console.log("today:     "+f4(sum(latest.filter(r=>day(r)===today))));
console.log("yesterday: "+f4(sum(latest.filter(r=>day(r)===d))));
console.log("total:     "+f4(sum(latest))+"  ("+latest.length+" sessions)");
const by=(key)=>{const m=new Map();for(const r of latest){const k=key(r)||"(unknown)";m.set(k,(m.get(k)||0)+cost(r));}return [...m.entries()].sort((a,b)=>b[1]-a[1]);};
console.log("\n=== By model ===");for(const [k,v] of by(r=>r.model))console.log(f4(v).padStart(12)+"  "+k);
console.log("\n=== Last 7 days ===");
const days=new Map();for(const r of latest){const k=day(r);days.set(k,(days.get(k)||0)+cost(r));}
[...days.entries()].sort((a,b)=>b[0]<a[0]?-1:1).slice(0,7).forEach(([k,v])=>console.log(k+"  "+f4(v)));
'

CSV export (/cost-report csv)

node -e '
const fs=require("fs"),os=require("os"),path=require("path");
const f=path.join(os.homedir(),".claude","metrics","costs.jsonl");
if(!fs.existsSync(f)){console.error("no data");process.exit(0);}
const rows=fs.readFileSync(f,"utf8").split(/\r?\n/).filter(Boolean).map(l=>{try{return JSON.parse(l)}catch{return null}}).filter(Boolean).slice(-100);
console.log("timestamp,session_id,model,input_tokens,output_tokens,cache_write_tokens,cache_read_tokens,estimated_cost_usd");
for(const r of rows)console.log([r.timestamp,r.session_id,r.model,r.input_tokens,r.output_tokens,r.cache_write_tokens,r.cache_read_tokens,r.estimated_cost_usd].join(","));
'

Report format

  1. Summary: today, yesterday, total, session count.
  2. By model: models ranked by total cost.
  3. Last seven days: date and cost.

Rely on the precomputed estimated_cost_usd values written by the tracker; do not re-estimate pricing from raw tokens here.