Anthropic Usage

Format for Anthropic API usage reports generated by anthropic-report.py. Use this skill when creating, modifying, or discussing the format of Anthropic proxy...

Security Scan

The skill's code, instructions, and requirements are coherent with its stated purpose (formatting and patching an Anthropic usage-report script); it does not request secrets or network access and only performs local file edits with a backup.

Purpose & Capability

Name/description describe formatting Anthropic usage reports and the package contains a report formatter, a patcher to insert that formatter into an existing anthropic-report.py, and a localization preset — all directly relevant to the stated purpose.

Instruction Scope

SKILL.md stays on-topic: it documents formatting rules, describes LANG localization, and instructs how to apply the reference formatter using patch_format.py. The patch script reads and overwrites a target Python script (creating a .pre-format-patch backup) — this is expected for a patch tool but means users should only run it on trusted files/paths.

Install Mechanism

No install spec, no downloads, and no external package installs — instruction-only with bundled reference scripts. This minimizes install-time risk.

Credentials

The skill requires no environment variables, binaries, or credentials. The code does not attempt to read secrets or network endpoints. It expects the target script to supply functions/objects such as get_pricing and CET timezone, which is reasonable for integrating the formatter.

Persistence & Privilege

always is false, and the skill does not request persistent system-wide privileges. The patch tool writes only the specified target file and a local backup; it does not modify other skills or global agent settings.

Assessment

This skill appears to do exactly what it says: add/replace a format_report implementation and provide localization. Before running patch_format.py, do a dry run (use --dry-run) and inspect the preview and the created backup (.py.pre-format-patch). Only run the patch on a trusted anthropic-report.py copy and verify the target defines the expected helpers (get_pricing, CET timezone, aggregate behavior) — otherwise the patched script may fail. Because the patcher overwrites files, avoid running it with elevated privileges or on system-wide scripts unless you have a backup and have reviewed the replacement function.

Anthropic Usage Report Format

Design Principles

1. Icons = signal importance only. Icons appear ONLY at the start of lines with key metrics the user needs to scan quickly. No decorative icons.
2. Key metrics first. CLI %, cache %, high-output call count — these appear at line start with icons.
3. No noise. No latency (ms), no success/error icons, no redundant breakdowns unless errors exist.
4. Neutral labeling. High-output calls are flagged for review, not pre-judged as "should have used CLI" — the cause may be inefficiency, legitimate work, or missing CLI usage.
5. Compact. Every line earns its place.

Report Template

Anthropic Usage — {date} ({time} CET)
══════════════════════════════════════════
Total: {total} calls ({errors} errors)
⚠️ CLI: {cli_pct}% / API: {api_pct}%
{agent_name}:
  🗄️ {cache_pct}% cache ({cache_read} read / {cache_create} create)
  Tokens: {total_in} in ({new_in} new) / {total_out} out
  Cost: ~${cost}
──────────────────────────────────────────
CLI potential:
  ⚠️ {n}× inline work (>{threshold} out, {sum} tok, max {max})
  {n}× standard ({low}-{threshold} out)
  {n}× heartbeat (<{low} out)
──────────────────────────────────────────
Total estimate: ~${total_cost}

Conditional Rules

• Error breakdown: Show API: X (Y ok, Z err) | CLI: X (Y ok, Z err) ONLY when errors > 0
• CLI icon: ⚠️ when CLI < 50%, ✅ when CLI >= 50%
• High output icon: ⚠️ when inline work calls > 0, ✅ (show "No inline work") when 0
• Model line: Show only if multiple models used

Icon Placement Rules

Icons appear ONLY on these lines, ALWAYS at line start:

• ⚠️ or ✅ — CLI/API ratio
• 🗄️ — Cache rate
• ⚠️ or ✅ — Inline work count

NO icons on: header, totals, tokens, cost, heartbeat count, standard count, separator lines.

Language

Default language is English. To localize, edit LANG dict in scripts/format_report.py:

LANG = {
    "total":        "Total",
    "calls":        "calls",
    "errors":       "errors",
    "cache":        "cache",
    "tokens":       "Tokens",
    "cost":         "Cost",
    "total_est":    "Total estimate",
    "cli_potential": "CLI potential",
    "inline_work":  "inline work",
    "standard":     "standard",
    "heartbeat":    "heartbeat",
    "no_calls":     "No API calls today.",
    "no_inline":    "No inline work",
}

Presets available in scripts/:

• lang_cs.py — Czech / Čeština

Implementation

Reference implementation: scripts/format_report.py

To apply to an existing installation:

python3 scripts/patch_format.py /path/to/anthropic-report.py