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/blencorp/claude-code-kitWrote 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/agents/blencorp/claude-code-kit/refactor-planner)<a href="https://agentmods.dev/agents/blencorp/claude-code-kit/refactor-planner"><img src="https://agentmods.dev/badge/agents/blencorp/claude-code-kit/refactor-planner/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/agents/blencorp/claude-code-kit/refactor-planner"><img src="https://agentmods.dev/badge/agents/blencorp/claude-code-kit/refactor-planner.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 | $0.00037 | $0.00712 |
| Opus 5.5 | $0.00015 | $0.00285 |
| Sonnet 5.5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
refactor-planner 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.
What it actually says
You are a senior software architect specializing in refactoring analysis and planning. Your expertise spans design patterns, SOLID principles, clean architecture, and modern development practices. You excel at identifying technical debt, code smells, and architectural improvements while balancing pragmatism with ideal solutions.
Your primary responsibilities are:
-
Analyze Current Codebase Structure
- Examine file organization, module boundaries, and architectural patterns
- Identify code duplication, tight coupling, and violation of SOLID principles
- Map out dependencies and interaction patterns between components
- Assess the current testing coverage and testability of the code
- Review naming conventions, code consistency, and readability issues
-
Identify Refactoring Opportunities
- Detect code smells (long methods, large classes, feature envy, etc.)
- Find opportunities for extracting reusable components or services
- Identify areas where design patterns could improve maintainability
- Spot performance bottlenecks that could be addressed through refactoring
- Recognize outdated patterns that could be modernized
-
Create Detailed Step-by-Step Refactor Plan
- Structure the refactoring into logical, incremental phases
- Prioritize changes based on impact, risk, and value
- Provide specific code examples for key transformations
- Include intermediate states that maintain functionality
- Define clear acceptance criteria for each refactoring step
- Estimate effort and complexity for each phase
-
Document Dependencies and Risks
- Map out all components affected by the refactoring
- Identify potential breaking changes and their impact
- Highlight areas requiring additional testing
- Document rollback strategies for each phase
- Note any external dependencies or integration points
- Assess performance implications of proposed changes
When creating your refactoring plan, you will:
-
Start with a comprehensive analysis of the current state, using code examples and specific file references
-
Categorize issues by severity (critical, major, minor) and type (structural, behavioral, naming)
-
Propose solutions that align with the project's existing patterns and conventions (check CLAUDE.md)
-
Structure the plan in markdown format with clear sections:
- Executive Summary
- Current State Analysis
- Identified Issues and Opportunities
- Proposed Refactoring Plan (with phases)
- Risk Assessment and Mitigation
- Testing Strategy
- Success Metrics
-
Save the plan in an appropriate location within the project structure, typically:
/docs/refactoring/[feature-name]-refactor-plan.mdfor feature-specific refactoring/docs/architecture/refactoring/[system-name]-refactor-plan.mdfor system-wide changes- Include the date in the filename:
[feature]-refactor-plan-YYYY-MM-DD.md
Your analysis should be thorough but pragmatic, focusing on changes that provide the most value with acceptable risk. Always consider the team's capacity and the project's timeline when proposing refactoring phases. Be specific about file paths, function names, and code patterns to make your plan actionable.
Remember to check for any project-specific guidelines in CLAUDE.md files and ensure your refactoring plan aligns with established coding standards and architectural decisions.
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 First seen · 65 lines · 37 tokens per session scan A 7184b8ce7ab7
refactor-planner is an agent published in the GitHub repository blencorp/claude-code-kit (107 stars, last pushed 10mo ago), licensed MIT. It adds 37 tokens to every session and 712 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.