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 commands/fujigo-software/f5-framework-claude/f5-classifygit clone --depth 1 https://github.com/Fujigo-Software/f5-framework-claudeWrote 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/commands/fujigo-software/f5-framework-claude/f5-classify)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-classify"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-classify.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 | $0.00018 | $0.05565 |
| Opus 5 | $0.00009 | $0.02782 |
| Sonnet 5 | $0.00004 | $0.01113 |
| Haiku 4.5 | $0.00002 | $0.00556 |
Grade A, and why
f5-classify 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-classify - Input Classification Command V3.0
Phân loại input files (Excel, documents) theo type, detect gaps, và tạo Coverage Declaration.
Version: 3.0 (Content-First Classification) Nguyên tắc: AI support - Human decide Thay đổi chính: Phân loại dựa trên NỘI DUNG file thay vì tên file
🎯 VAI TRÒ CỦA F5-CLASSIFY
┌─────────────────────────────────────────────────────────────────────────────────┐
│ f5-classify KHÔNG PHẢI là bước tạo spec │
│ f5-classify KHÔNG quyết định đúng/sai nội dung │
├─────────────────────────────────────────────────────────────────────────────────┤
│ VAI TRÒ ĐÚNG: │
│ ✅ Phân loại tài liệu theo type (dựa trên CONTENT) │
│ ✅ Trích xuất thông tin có cấu trúc │
│ ✅ Khai báo độ bao phủ (Coverage Declaration) │
│ ✅ Khai báo chất lượng (Classification Quality Level) │
│ ✅ Khai báo giới hạn kỹ thuật (Technical Limitations) │
│ ✅ Gắn cờ rủi ro (Missing Sections, Low Confidence) │
│ ✅ Chuẩn hoá input cho các phase phía sau │
├─────────────────────────────────────────────────────────────────────────────────┤
│ QUYẾT ĐỊNH CUỐI CÙNG: BA / DEV / Tech Lead │
└─────────────────────────────────────────────────────────────────────────────────┘
🆕 WHAT'S NEW IN V3.0
| Feature | V2.1 | V3.0 |
|---|---|---|
| Classification method | Name-based (tên file) | Content-first (nội dung) |
| Accuracy | Phụ thuộc naming convention | Dựa trên nội dung thực tế |
| Confidence | Based on name pattern match | Based on content analysis depth |
| Fallback | None | Name-based khi không đọc được content |
🧠 CLASSIFICATION LOGIC V3.0 - CONTENT-FIRST
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.
- 4d ago First seen · 619 lines · 18 tokens per session scan A 19fe316c3679
f5-classify is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 5,565 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 2026-08-30.
Other commands, from other repositories
build
Guided feature development with approval gates at each phase.
plan
Project spec (no args) or feature FRD (with args).
ship
Autonomous spec-to-PR pipeline with zero approval gates.
debug
Structured debugging with parallel investigation agents.
init
Analyze codebase and generate CLAUDE.md with project conventions.
release
Generate changelog, bump version, and create git tag.