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.
npx skills add ericwang915/PythonClaw --skill model_usagegit clone --depth 1 https://github.com/ericwang915/PythonClawWrote 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/skills/ericwang915/pythonclaw/model_usage)<a href="https://agentmods.dev/skills/ericwang915/pythonclaw/model_usage"><img src="https://agentmods.dev/badge/skills/ericwang915/pythonclaw/model_usage/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/skills/ericwang915/pythonclaw/model_usage"><img src="https://agentmods.dev/badge/skills/ericwang915/pythonclaw/model_usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00453 |
| Opus 5.5 | $0.00025 | $0.00181 |
| Sonnet 5.5 | $0.00012 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
model_usage 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.
What it actually says
Model Usage
Track and display LLM token usage, costs, and session statistics.
When to Use
✅ USE this skill when:
- "How many tokens have I used?"
- "What's my API cost so far?"
- "Show me model usage stats"
- "How many messages in this session?"
- "Which model am I using?"
When NOT to Use
❌ DON'T use this skill when:
- Changing the LLM model or provider → use
change_setting - Viewing conversation content → use
session_logs - Checking system status → check agent status directly
Usage
Current session stats
python {skill_path}/usage_stats.py
Check detailed interaction log
The history_detail.jsonl file under ~/.pythonclaw/context/logs/ contains
structured records of every agent interaction, including:
- Input messages
- Tool calls and results
- LLM responses
- Timestamps
python {skill_path}/usage_stats.py --log ~/.pythonclaw/context/logs/history_detail.jsonl
Quick stats via jq (if installed)
# Count total interactions
wc -l ~/.pythonclaw/context/logs/history_detail.jsonl
# Recent entries
tail -5 ~/.pythonclaw/context/logs/history_detail.jsonl | python -m json.tool
Notes
- Token counts are estimates based on message length
- Cost calculation requires knowing the model's pricing (not tracked automatically)
- The
history_detail.jsonlis append-only and grows over time - Use
/statuscommand in chat for quick session info
Resources
| File | Description |
|---|---|
usage_stats.py |
Parse and summarise usage from history logs |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 62 tokens per session scan A ae4d61cd3d32
model_usage is a skill published in the GitHub repository ericwang915/PythonClaw (45 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 453 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
tencent-channel-community
A command-line skill for managing Tencent Channels, QQ-based online communities where members communicate through channels, posts, comments, and private messages.
skill-creator
A guide for creating or improving an agent skill: a SKILL.md file that gives an AI a repeatable workflow for a specific task. It covers the skill’s name, search keywords, instructions, failure handling, and examples where needed.
memory-consolidate
A memory-maintenance skill that stores a small number of durable, searchable facts and keeps the main memory file concise.
qrcode
A tool that creates a PNG QR code from text or a web address. A QR code is a square image that phones can scan to recover the encoded content.
short-url
A tool that turns a long web address into a shorter link using the is.gd service. The input must be a valid HTTP or HTTPS address.
line
A LINE Messaging API connection for receiving and sending chat messages through webhooks. LINE is a messaging platform; a webhook is a web address that receives event notifications from a service.