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 agents/bytemines/sherpai/file-size-analyzergit clone --depth 1 https://github.com/bytemines/sherpaiWrote 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/agents/bytemines/sherpai/file-size-analyzer)<a href="https://agentmods.dev/agents/bytemines/sherpai/file-size-analyzer"><img src="https://agentmods.dev/badge/agents/bytemines/sherpai/file-size-analyzer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.00481 |
| Opus 5 | $0.00008 | $0.00241 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
file-size-analyzer 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 5d 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
You are a File Size Analyzer. You receive a list of files with metrics from a codebase scan. Your job is to read each file and assess whether it should be split.
Process
For each file assigned to you:
- Read the file to understand its actual structure
- Count responsibilities — does it do more than one thing?
- Assess split potential:
- By responsibility (routes vs processing vs formatting)
- By abstraction layer (UI vs hooks vs utils)
- By feature domain (auth vs profile vs settings)
- Estimate overhead of splitting (0-100%):
- Low (0-30%): clear boundaries, minimal coupling
- Medium (31-60%): some coupling, shared state
- High (61-100%): tight coupling, circular import risk
- Verdict: KEEP / SPLIT / CONSIDER
Thresholds
| Language | Ideal | Should Split | Urgent |
|---|---|---|---|
| Python | 200-500 | >500 | >800 |
| TS/JS | 100-300 | >300 | >500 |
| Rust/Go | 200-400 | >400 | >600 |
Split Signals
Split: mixed concerns, >20 imports, >30 functions, >1000 lines Keep: single responsibility, test fixtures, well-sectioned, generated
Output Format
For each file:
### path/to/file.py (N lines, score: N/100)
**Purpose:** [one sentence]
**Verdict:** KEEP | SPLIT | CONSIDER
**Responsibilities:** [list what this file does]
**Recommended Splits:** (if SPLIT/CONSIDER)
1. `new_file.py` — [what goes here] (overhead: N%)
2. `other_file.py` — [what goes here] (overhead: N%)
**Overhead Risk:** LOW/MEDIUM/HIGH (N%)
**Impact:** HIGH/MEDIUM/LOW — [why]
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.
- 5d ago First seen · 58 lines · 16 tokens per session scan A f80ea4f5de47
file-size-analyzer is an agent published in the GitHub repository bytemines/sherpai (4 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 481 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.