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.
git clone --depth 1 https://github.com/muyen/vibe-to-prodWrote 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/muyen/vibe-to-prod/improve-claude-config)<a href="https://agentmods.dev/commands/muyen/vibe-to-prod/improve-claude-config"><img src="https://agentmods.dev/badge/commands/muyen/vibe-to-prod/improve-claude-config/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/muyen/vibe-to-prod/improve-claude-config"><img src="https://agentmods.dev/badge/commands/muyen/vibe-to-prod/improve-claude-config.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00869 |
| Opus 5.5 | $0.00007 | $0.00348 |
| Sonnet 5.5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
improve-claude-config 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 12d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Configuration Improvement
Run periodic review and optimization of Claude Code configuration.
Scope: $ARGUMENTS
1. Research Phase
Check Latest Best Practices
Search for the latest Claude Code best practices:
- CLAUDE.md organization and structure
- Hooks - types, use cases, best practices
- Skills vs Commands - when to use each
- Settings and permissions
Use: claude-code-guide agent or web search for "Claude Code CLI best practices 2025"
2. Audit Current Configuration
File Structure Check
# List all Claude config files
find .claude -type f \( -name "*.md" -o -name "*.json" -o -name "*.sh" \) | sort
# Check file sizes
wc -l CLAUDE.md .claude/rules/*.md .claude/skills/**/SKILL.md 2>/dev/null
Configuration Inventory
| Component | Location | Count |
|---|---|---|
| Main memory | CLAUDE.md |
1 |
| Rules | .claude/rules/ |
? |
| Skills | .claude/skills/ |
? |
| Commands | .claude/commands/ |
? |
| Hooks | .claude/hooks/ |
? |
Check for Issues
- CLAUDE.md Size: Should be < 150 lines
- Rules Have Paths: All rules should have
paths:frontmatter - Skills Have Description: Skills need clear
description:for activation triggers - Hooks Registered: All hooks in
.claude/hooks/should be insettings.json - Settings Security: Check deny rules for secrets
- Settings Schema: Must use
"$schema": "https://json.schemastore.org/claude-code-settings.json"
3. Identify Improvements
Checklist
Structure:
- CLAUDE.md is focused (only cross-cutting rules)
- Platform rules are in
.claude/rules/with path conditions - No duplicate rules across files
Security:
-
settings.jsonhas deny rules for.env, secrets, keys - Sandbox is enabled
Efficiency:
- Commands that should be proactive are converted to skills
- Hooks are fast (< 30s timeout)
Team:
-
settings.jsonis committed (team-shared) -
settings.local.jsonis gitignored (personal)
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.
- 12d ago First seen · 153 lines · 18 tokens per session scan A 35e240eb777c
improve-claude-config is a command published in the GitHub repository muyen/vibe-to-prod (34 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 869 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other commands, from other repositories
clarify
Reduce spec ambiguity via targeted questions with adaptive auto-invocation (planning is 80% of success).
ultrathink
Enter deep craftsman mode - question everything, plan like Da Vinci, craft insanely great solutions, then materialize to roadmap.
init
Initialize project documentation, preferences, or design tokens.
quick-fix
Fast-track workflow for small bug fixes.
help
Category: System Syntax: /help [command|topic].
plan-status
Render the current plan tree. Alias for /aura-frog:plan status (v3.7.2+).