Lewati ke konten
TakoAPI
Kembali ke skill

trustlog-guard

oleh anouartrust

Coding Agents & IDEs
259Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Financial governance for OpenClaw agents.

Deskripsi

Apa yang Dilakukan Skill Ini

Reads OpenClaw agent session logs to track API spending by model and session. Enforces daily and monthly budgets, detects anomalies like runaway loops and model escalations, and produces formatted cost reports. All processing is local with no external connections.

Unlike cloud-based cost monitoring tools, it reads spend data directly from local session files with no external accounts, API keys, or data transmission required.

Kapan Menggunakannya

  • Reviewing total API spend after a long agent session
  • Setting a daily budget limit to prevent unexpected charges
  • Spotting an agent stuck in a message loop before costs escalate
  • Identifying which AI model is consuming the most budget
  • Finding which sessions drove the highest spending this month

Contoh Alur Kerja

INPUT

User asks: /trustlog

AGENT
  1. 1

    Scans ~/.openclaw/agents/{agent}/sessions/*.jsonl for cost records

  2. 2

    Groups message costs by today, this week, and this month

  3. 3

    Ranks top sessions by total spend and message count

  4. 4

    Runs anomaly checks for burn rate spikes, rapid-fire loops, and model escalations

  5. 5

    Appends optimization tips based on model usage patterns and cache efficiency

OUTPUT

Full financial report with spending overview, cost breakdown by model, top sessions, anomaly scan results, and one actionable optimization tip

Instalasi

clawhub install anouartrust/trustlog-guard

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan