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-designgit 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-design)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-design"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-design.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 | $0.00011 | $0.06183 |
| Opus 5 | $0.00005 | $0.03092 |
| Sonnet 5 | $0.00002 | $0.01237 |
| Haiku 4.5 | $0.00001 | $0.00618 |
Grade A, and why
f5-design 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.
How it starts
The opening of the file, as written. The whole thing — 746 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-design - Unified Design & Specification Command
Consolidated command that replaces:
/f5-spec→/f5-design spec
Manage and generate design documents (Basic Design 基本設計, Detail Design 詳細設計) and specifications (SRS, Use Cases, Business Rules).
ARGUMENTS
The user's request is: $ARGUMENTS
MODE DETECTION
| Pattern | Mode | Description |
|---|---|---|
spec <action> |
SPEC | SRS, Use Cases, Business Rules (D1-D2) |
<other> (default) |
DESIGN | Architecture, DB, API, Screens (D3-D4) |
⚠️ CRITICAL OUTPUT RULES
KHÔNG ĐƯỢC tạo files ở docs/, output/, hoặc thư mục khác.
BẮT BUỘC tuân theo cấu trúc sau:
Basic Design (D3)
| Command | Document Type | Output Path |
|---|---|---|
generate architecture |
Architecture | .f5/specs/basic-design/v{VERSION}/system-architecture.md |
generate tables |
Database (all) | .f5/specs/basic-design/v{VERSION}/database/database-design.md |
generate table <name> |
Database (single) | .f5/specs/basic-design/v{VERSION}/database/{table-name}.md |
generate api-list |
API (all) | .f5/specs/basic-design/v{VERSION}/api/api-design.md |
generate api <endpoint> |
API (single) | .f5/specs/basic-design/v{VERSION}/api/{METHOD}-{endpoint}.md |
generate screen-list |
Screens (all) | .f5/specs/basic-design/v{VERSION}/screens/screen-list.md |
generate screen <name> |
Screens (single) | .f5/specs/basic-design/v{VERSION}/screens/{screen-name}.md |
generate batch <name> |
Batch Specs | .f5/specs/basic-design/v{VERSION}/batch/{batch-name}.md |
generate erd |
ERD Diagram | .f5/specs/basic-design/v{VERSION}/diagrams/erd.md |
Detail Design (D4)
| Command | Document Type | Output Path |
|---|---|---|
generate screen-detail <name> |
Screen Details | .f5/specs/detail-design/v{VERSION}/screens/{screen-name}.md |
generate api-detail <endpoint> |
API Details | .f5/specs/detail-design/v{VERSION}/api/{endpoint}.md |
generate batch-detail <name> |
Batch Details | .f5/specs/detail-design/v{VERSION}/batch/{batch-name}.md |
generate component <name> |
Component Specs | .f5/specs/detail-design/v{VERSION}/components/{component}.md |
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 · 746 lines · 11 tokens per session scan A 1a1ba52d234e
f5-design is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 6,183 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.