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 agentmods add skills/victorzhong0110/skill-evolution/code-statsnpx skills add victorzhong0110/skill-evolution --skill code-statsgit clone --depth 1 https://github.com/victorzhong0110/skill-evolutionWhat 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 | $0.00091 | $0.00529 |
| Opus 5 | $0.00046 | $0.00264 |
| Sonnet 5 | $0.00018 | $0.00106 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
code-stats 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 2d 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.
This is a copy
88% identical to code-stats — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Code Stats Skill
Analyzes code files and generates statistics about a codebase.
Usage
When invoked, this skill will:
- Scan the specified directory (defaults to current directory)
- Count total lines and files by extension
- Report the largest files
- Output results in a structured format
- Sort extension summaries by total line count in descending order
Prefer the bundled script scripts/count_stats.py over re-implementing find /
wc by hand. Pass the target directory as the first argument.
Output Format
Always use this exact format for the output:
# Code Statistics
## Summary
- Total Files: <count>
- Total Lines: <count>
- Total Size: <size_bytes> bytes
## Files by Extension
| Extension | Files | Lines |
|-----------|-------|-------|
| .go | 12 | 1500 |
| .md | 5 | 200 |
## Top 5 File Extensions by Line Count
1. .go — 1500 lines
2. .md — 200 lines
## Largest Files (top 5)
1. main.go (500 lines)
2. util.go (300 lines)
If a file has no extension, group it under (no ext) in both extension sections.
Process
- Run
python3 scripts/count_stats.py <dir>when the script is available - Otherwise locate files, count lines, and aggregate locally
- Group files with no extension under
(no ext) - Sort both extension summaries by total line count in descending order
- Aggregate the results into the output format above
- If no directory is specified, analyze the current working directory
Examples
- "Analyze the current directory"
- "Run code-stats on ./src"
- "Show me file type distribution"
- "How many lines of Python do we have?"
What ships with it
9 files 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.
- 2d ago First seen · 71 lines · 91 tokens per session scan A b5caaeebddac
code-stats is a skill published in the GitHub repository victorzhong0110/skill-evolution (10 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 529 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to code-stats, differing in 15 lines, and is treated as a copy.
Other skills, from other repositories
tilelang-cuda-examples-torch
PyTorch + TileLang CUDA 完整示例代码.
pypto-case-matmul-2d
模式 B 示例：2D 矩阵乘法 + M 维 loop 分块 + 尾部处理.
pypto-case-reduction-sum
单轴归约示例：3D Sum reduction — 保持原始维度，最简 kernel.
pypto-case-norm-batchnorm
模式 C 示例：3D Norm — BatchNorm，展示 3D 降维、连续单轴 sum 多维归约、expandclone 广播.
pypto-case-loss-crossentropy
模式 D 示例：Loss — CrossEntropyLoss，展示多输入 kernel、两段 tile、softmax+gather+sum、标量输出.
pypto-case-norm-layernorm
模式 C 示例：2D Norm + Loop — LayerNorm，展示 forward 降维为 2D、kernel 内 sum 归约 + 归一化.