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-improvegit 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-improve)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-improve"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-improve.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 | $0.00005 | $0.04711 |
| Opus 5 | $0.00003 | $0.02355 |
| Sonnet 5 | $0.00001 | $0.00942 |
| Haiku 4.5 | $0.00001 | $0.00471 |
Grade A, and why
f5-improve 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 — 822 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-improve - Code Improvement & Optimization
Purpose: Analyze code and apply systematic improvements Version: 1.0.0 Category: Quality Inspiration: SuperClaude /sc:improve
Command Syntax
# Basic - analyze and preview improvements
/f5-improve [path]
# With improvement type
/f5-improve [path] --type <quality|performance|security|maintainability|all>
# With apply mode
/f5-improve [path] --preview # Preview only (default)
/f5-improve [path] --safe # Apply low-risk changes only
/f5-improve [path] --interactive # Confirm each change
/f5-improve [path] --auto # Apply all automatically
# With validation
/f5-improve [path] --validate # Run tests after applying
# Combined
/f5-improve src/services/ --type performance --preview
/f5-improve auth-module --type security --safe --validate
ARGUMENTS
The user's request is: $ARGUMENTS
STEP 1: PARSE ARGUMENTS
Parse from $ARGUMENTS:
parsed:
path: "[extracted path or 'src/' default]"
type: "[quality|performance|security|maintainability|all]"
mode: "[preview|safe|interactive|auto]"
validate: "[true|false]"
Default values:
- path:
src/or current directory - type:
all - mode:
preview - validate:
false
STEP 2: DETECT STACK & LOAD CONFIG
Read stack from project files (package.json, pom.xml, pyproject.toml, etc.):
| Indicator | Stack | Language |
|---|---|---|
@nestjs/core |
NestJS | TypeScript |
spring-boot |
Spring | Java |
fastapi |
FastAPI | Python |
go.mod |
Go | Go |
flutter |
Flutter | Dart |
next |
Next.js | TypeScript |
vue |
Vue | TypeScript/JS |
angular |
Angular | TypeScript |
laravel |
Laravel | PHP |
Load improve config from .f5/config/improve.yaml if exists.
Output
## Configuration
| Setting | Value |
|---------|-------|
| Stack | NestJS (TypeScript) |
| Path | src/services/ |
| Type | performance |
| Mode | preview |
| Validate | false |
Excluded:
- **/*.spec.ts
- **/node_modules/**
- **/dist/**
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 · 822 lines · 0 tokens per session scan A d86eab833eec
f5-improve is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 5 tokens to every session and 4,711 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.