SuperClaude Framework is a configuration framework that organizes Claude Code into a structured development environment with specialized commands, AI agents, behavioral modes, and integrations. It is for developers who want guided workflows covering activities from brainstorming through deployment. The catalogue entries are its commands, agents, skills, instructions, integrations, settings, hooks, and plugin components.
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/SuperClaude-Org/SuperClaude_FrameworkWrote 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/superclaude-org/superclaude_framework/improve)<a href="https://agentmods.dev/commands/superclaude-org/superclaude_framework/improve"><img src="https://agentmods.dev/badge/commands/superclaude-org/superclaude_framework/improve/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/superclaude-org/superclaude_framework/improve"><img src="https://agentmods.dev/badge/commands/superclaude-org/superclaude_framework/improve.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 | $0.00015 | $0.00796 |
| Opus 5.5 | $0.00006 | $0.00318 |
| Sonnet 5.5 | $0.00003 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sc:improve - Code Improvement
Triggers
- Code quality enhancement and refactoring requests
- Performance optimization and bottleneck resolution needs
- Maintainability improvements and technical debt reduction
- Best practices application and coding standards enforcement
Usage
/sc:improve [target] [--type quality|performance|maintainability|style] [--safe] [--interactive]
Behavioral Flow
- Analyze: Examine codebase for improvement opportunities and quality issues
- Plan: Choose improvement approach and activate relevant personas for expertise
- Execute: Apply systematic improvements with domain-specific best practices
- Validate: Ensure improvements preserve functionality and meet quality standards
- Document: Generate improvement summary and recommendations for future work
Key behaviors:
- Multi-persona coordination (architect, performance, quality, security) based on improvement type
- Framework-specific optimization via Context7 integration for best practices
- Systematic analysis via Sequential MCP for complex multi-component improvements
- Safe refactoring with comprehensive validation and rollback capabilities
MCP Integration
- Sequential MCP: Auto-activated for complex multi-step improvement analysis and planning
- Context7 MCP: Framework-specific best practices and optimization patterns
- Persona Coordination: Architect (structure), Performance (speed), Quality (maintainability), Security (safety)
- Availability fallback: The MCP servers named here are preferred tooling, not hard requirements — when one is not installed, degrade gracefully (native reasoning in place of Sequential, official docs via web lookup in place of Context7, native tools otherwise) instead of routing work to absent servers.
Tool Coordination
- Read/Grep/Glob: Code analysis and improvement opportunity identification
- Edit/MultiEdit: Safe code modification and systematic refactoring
- TodoWrite: Progress tracking for complex multi-file improvement operations
- Task: Delegation for large-scale improvement workflows requiring systematic coordination
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.
- 1mo ago Changed 8ab1a6e8a8b6
- 1mo ago First seen · 95 lines · 15 tokens per session scan A 03a5c6dec19d
improve is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,905 stars, last pushed 20d ago), licensed MIT. It adds 15 tokens to every session and 796 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 2026-08-30.
Other commands, from other repositories
spec-review
A command for reviewing an OpenSpec proposal with two separate AI models. OpenSpec is a way to describe planned software changes before implementation.
impl-review
John Carmack-level implementation review via Codex, Copilot, Cursor, Claude or a host reviewer.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
spec-completion-review
Spec completion review - verify implementation matches spec.
code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding.
review-team
Parallel code review with 3 specialist lenses plus the kit-default kit:advisor extra lens. Dispatches the security, architecture, and test-coverage lenses simultaneously, adds the cross-cutting kit:advisor (critique mode), then merges findings.