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-helpgit 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-help)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-help"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-help.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 | $0.00013 | $0.02612 |
| Opus 5 | $0.00006 | $0.01306 |
| Sonnet 5 | $0.00003 | $0.00522 |
| Haiku 4.5 | $0.00001 | $0.00261 |
Grade A, and why
f5-help 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
F5 Help - Smart Contextual Assistant
Usage
/f5-help # Show status + next actions
/f5-help --quickstart # 5-minute getting started
/f5-help --next # Single next action
/f5-help --resume # Resume previous session
/f5-help --stuck # Troubleshooting help
/f5-help "task description" # Specific task guidance
/f5-help <topic> # Topic help (gates, workflow, commands, agents)
Context Detection
First, analyze current state by checking:
1. Project Initialization
# Check if F5 is initialized
ls -la .f5/ 2>/dev/null
If .f5/ doesn't exist → Project not initialized
2. Current Gate & Workflow
# Read current state
cat .f5/manifest.yaml 2>/dev/null
cat .f5/gates-status.yaml 2>/dev/null
cat .f5/session.yaml 2>/dev/null
3. Recent Activity
# Check recent file changes
git status --short 2>/dev/null | head -10
# Check session file if exists
cat .f5/session.json 2>/dev/null
Response Format
For No Arguments (Default)
📍 Current Status:
Project: [initialized/not initialized]
Workflow: [workflow name or "none"]
Phase: [X/Y (phase name)]
Gate: [gate ID (gate name)]
Mode: [mode] | Persona: [persona]
✅ Completed (this phase):
• [completed item 1]
• [completed item 2]
📋 Next Actions:
1. [action 1 with command]
2. [action 2 with command]
3. [action 3 with command]
🎯 Suggested Command:
[most appropriate next command with example]
💡 Tips:
• [relevant tip 1]
• [relevant tip 2]
For --quickstart
Provide 5-minute getting started guide:
🚀 F5 Framework - 5 Minute Quickstart
F5 Framework is an AI-powered development toolkit that guides you through
documentation-first development with quality gates (D1-D4, G2-G4).
📋 Step 1: Initialize (30 seconds)
/f5-init
This creates .f5/ configuration and sets up quality gates.
📋 Step 2: Load Workflow (30 seconds)
/f5-load
Auto-detects your stack and asks 2 questions:
• Starting point (requirements/basic-design/detail-design)
• Project type (poc/mvp/production)
📋 Step 3: Check Status (10 seconds)
/f5-status
Shows current gate, pending items, and progress.
📋 Step 4: Start Working
Based on your gate:
• D1-D2: /f5-research, /f5-ba
• D3-D4: /f5-design, /f5-spec
• G2: /f5-implement
• G3: /f5-test
📋 Step 5: Get Help Anytime
/f5-help # What to do next
/f5-help --stuck # Troubleshooting
/f5-help "your task" # Task-specific guidance
⏱️ Total setup time: ~2 minutes
🎯 You're ready to go!
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 · 422 lines · 13 tokens per session scan A b0f98143ab0f
f5-help is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 2,612 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.