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-questiongit 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-question)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-question"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-question.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 | $0.00008 | $0.03369 |
| Opus 5 | $0.00004 | $0.01684 |
| Sonnet 5 | $0.00002 | $0.00674 |
| Haiku 4.5 | $0.00001 | $0.00337 |
Grade A, and why
f5-question 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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-question - Q&A Tracking Command
Quản lý câu hỏi và clarification requests trong workflow.
Usage
/f5-question raise --from <source> --severity <level> --tag <tag>
/f5-question list [--status open|resolved|all] [--tag <tag>]
/f5-question show <Q-ID>
/f5-question resolve <Q-ID> --answer "<answer>"
Arguments
raise: Tạo câu hỏi mớilist: Xem danh sách Q&Ashow: Xem chi tiết một Q&Aresolve: Đánh dấu đã giải đáp
STEP 1: PARSE SUBCOMMAND
| Pattern | Action |
|---|---|
raise |
Go to [ACTION: RAISE] |
list |
Go to [ACTION: LIST] |
show <Q-ID> |
Go to [ACTION: SHOW] |
resolve <Q-ID> |
Go to [ACTION: RESOLVE] |
| (default) | Go to [ACTION: HELP] |
ACTION: RAISE
Tạo câu hỏi mới
Parameters:
--from <source>: Nguồn của câu hỏi (required)input,classification,DI-SCR-xxx(Phase 1)specs,srs,use-cases(Phase 2)design,basic-design,detail-design(Phase 3)technical-design,api-contract,data-model(Phase 4)
--severity <level>: Mức độ nghiêm trọng (required)blocking: Không thể tiếp tục implementnon-blocking: Có thể implement với assumption
--tag <tag>: Nhãn phân loại (required)DESIGN-GAP,MISSING-STATE,MISSING-ERROR,MISSING-VALIDATIONMISSING-EDGE-CASE,BUSINESS-RULE,REQUIREMENT-UNCLEARCONSTRAINT,DATA-FORMAT,INTEGRATION,PERFORMANCE,SECURITY
--source <file>: File/artifact cụ thể (optional)--assignee <role>: Người cần trả lời (optional, default: BA)
Process:
-
Đọc _index.yaml để lấy next ID:
# Check .f5/questions/_index.yaml # Get last Q-ID, increment by 1 -
Tạo file Q&A mới:
.f5/questions/open/Q-{ID}.md -
Update _index.yaml
-
Hiển thị kết quả
Output Format:
╔═══════════════════════════════════════════════════════════════════════════╗
║ 📝 TẠO CÂU HỎI MỚI ║
╠═══════════════════════════════════════════════════════════════════════════╣
ID: Q-{ID}
Trạng thái: 🟡 OPEN
Metadata:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Field | Value |
|-------|-------|
| **From** | {source} |
| **Source File** | {source_file} |
| **Severity** | {severity} |
| **Tag** | {tag} |
| **Assignee** | {assignee} |
| **Created** | {date} |
NỘI DUNG CÂU HỎI:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Claude sẽ prompt user nhập nội dung câu hỏi]
FILE ĐÃ TẠO:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
→ .f5/questions/open/Q-{ID}.md
→ .f5/questions/_index.yaml (updated)
BƯỚC TIẾP THEO:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Chờ BA/Customer trả lời trong file Q-{ID}.md
2. Sau khi có answer, chạy: /f5-question resolve Q-{ID}
╚═══════════════════════════════════════════════════════════════════════════╝
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 · 493 lines · 8 tokens per session scan A 72365c301c88
f5-question is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 3,369 once invoked, about $0.0000 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
paul:add-phase
Add a new phase to current milestone.
build
Guided feature development with approval gates at each phase.
ship
Autonomous spec-to-PR pipeline with zero approval gates.
debug
Structured debugging with parallel investigation agents.
release
Generate changelog, bump version, and create git tag.
review
Multi-agent code review with parallel validation.