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-modegit 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-mode)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-mode"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-mode.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 | $0.00004 | $0.02452 |
| Opus 5 | $0.00002 | $0.01226 |
| Sonnet 5 | $0.00001 | $0.00490 |
| Haiku 4.5 | $0.00000 | $0.00245 |
Grade A, and why
f5-mode 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-mode - Behavioral Mode Command
Manage and switch behavioral modes for context-aware responses.
ARGUMENTS
$ARGUMENTS
OVERVIEW
BEHAVIORAL MODES
═══════════════════════════════════════════════════════════════════
Modes adjust Claude's behavior for different contexts:
💻 coding │ Code-focused, minimal explanation
🎨 creative │ Innovative, exploratory
🔬 analytical │ Data-driven, systematic
📚 teaching │ Educational, step-by-step
🐛 debugging │ Problem-solving, diagnostic
👀 review │ Critical, constructive feedback
📋 planning │ Strategic, organized
🔒 security │ Paranoid, threat-aware
⚡ performance │ Optimization-focused
═══════════════════════════════════════════════════════════════════
SUBCOMMANDS
| Command | Description |
|---|---|
list |
List all available modes |
show <mode> |
Show mode details |
set <mode> |
Activate a mode |
reset |
Return to default mode |
auto [on|off] |
Toggle auto-detection |
status |
Show current mode |
ACTION: LIST_MODES
/f5-mode list
Display all available behavioral modes:
## 🎭 Available Modes
| Emoji | Mode | Description | Verbosity |
|-------|------|-------------|-----------|
| 💻 | coding | Code-focused output | 2 |
| 🎨 | creative | Innovative approach | 4 |
| 🔬 | analytical | Data-driven analysis | 4 |
| 📚 | teaching | Educational guidance | 5 |
| 🐛 | debugging | Systematic problem-solving | 3 |
| 👀 | review | Code review perspective | 3 |
| 📋 | planning | Strategic thinking | 4 |
| 🔒 | security | Security-focused | 4 |
| ⚡ | performance | Optimization-focused | 3 |
### Current: {{CURRENT_MODE}}
### Auto-detection: {{AUTO_STATUS}}
ACTION: SHOW_MODE
/f5-mode show <mode>
Display detailed information about a specific mode:
## 🔒 Security Mode
### Overview
Security-focused, paranoid approach to development.
### Characteristics
| Aspect | Value |
|--------|-------|
| Tone | Cautious, thorough |
| Verbosity | 4 (detailed) |
| Creativity | Low |
| Risk Tolerance | Zero |
### Behaviors
- Assume threats exist
- Validate all inputs
- Check OWASP Top 10
- Consider attack vectors
- Defense in depth
- Least privilege principle
### Triggers (Auto-Detection)
**Keywords:** security, auth, password, encrypt, sensitive, vulnerability
### Output Preferences
- Include threat analysis
- Show mitigations
- OWASP compliance check
- Security headers review
### Use Cases
- Authentication implementation
- Authorization logic
- Sensitive data handling
- API security
- Input validation
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 · 473 lines · 4 tokens per session scan A b9f9310f4d3f
f5-mode is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 4 tokens to every session and 2,452 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
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.