subagent

technical-debt-manager — Claude Code subagent: how to install

Q: How to install technical-debt-manager in Claude Code?

Run `npx claude-code-templates@latest --agent development-tools/technical-debt-manager` in your terminal. The agent template will be placed in `.claude/agents/technical-debt-manager.md`.

Q: Which tools does this agent require?

It operates through Claude Code capabilities including `Read`, `Grep`, `Bash`, `TodoWrite`, and `WebFetch`. Local access to `git` and project linters will improve scan accuracy.

Scans codebases for architecture flaws and test gaps. Helps build a prioritized refactoring plan for sprint planning.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --agent development-tools/technical-debt-manager

Open on GitHub

What technical-debt-manager does

This subagent inspects codebases across seven debt categories. It tracks cyclomatic complexity alongside vulnerable dependencies. To rate issue urgency, it calculates an impact score comparing 90-day git churn against test coverage.

Operation relies on built-in tools like Bash, Read, Grep, TodoWrite, and WebFetch. Without local linters or parsers installed, the agent falls back to basic shell commands.

The resulting backlog groups findings into four distinct tiers. Every action item comes with clear risk criteria.

What it helps with

Detect code duplication and excessive cyclomatic complexity
Spot vulnerable or outdated package dependencies
Prioritize refactoring tasks using git commit churn and test metrics
Structure a backlog of technical debt for the upcoming sprint

Example prompts for the agent

Audit this repository and highlight modules with high git churn and low test coverage
Check project dependencies for deprecated packages and security vulnerabilities
Draft a refactoring plan for our core services before the next sprint

How to install technical-debt-manager

1claude-code-templates

npx claude-code-templates@latest --agent development-tools/technical-debt-manager

2Manually: put the files in place

.claude/agents/technical-debt-manager.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Manually: put the files in place

.codex/agents/technical-debt-manager.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/technical-debt-manager.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about technical-debt-manager

How to install technical-debt-manager in Claude Code?

Run npx claude-code-templates@latest --agent development-tools/technical-debt-manager in your terminal. The agent template will be placed in .claude/agents/technical-debt-manager.md.

What does technical-debt-manager do?

It catalogs technical debt across design, testing, code quality, and infrastructure, ranking findings to deliver a structured refactoring roadmap.

Which tools does this agent require?

It operates through Claude Code capabilities including Read, Grep, Bash, TodoWrite, and WebFetch. Local access to git and project linters will improve scan accuracy.

Similar subagents

All subagents for Code review and refactoring →

code-reviewer official Anthropic Reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. 31,050installs code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. 31,050installs security-auditor official Anthropic This subagent searches code for security flaws and gives engineers concrete fixes. Use it to review a project before hardening or modernization work. 10,718installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. 9,715installs code-reviewer VoltAgent Community Reviews code changes for bugs, security flaws and maintenance issues. Use it before merging complex work or auditing a project. 31,050installs debugger VoltAgent Community Diagnoses software failures, reads stack traces, and isolates root causes to fix elusive bugs. Helpful when logs alone do not explain a crash. 13,459installs

From the same set804

The whole set →

create-feature Builds a new feature scaffold with implementation guidance, tests, and docs. Use it when a feature needs a structured path from planning to review. 898installs api-architect Designs REST and GraphQL APIs and prepares service-connection code. Use it to compare API styles or plan resilience and authentication. 881installs build-on-change Runs your build pipeline automatically whenever Claude Code edits a file. Detects build setups for Node.js, Make, Rust, and Java projects. 877installs metadata-agent Standardizes frontmatter in Obsidian markdown vaults. It detects missing metadata, inserts tags, file categories, and creation dates. 868installs market-research-analyst A Claude subagent that gathers market and competitor data through web search and returns it as a structured research report. 851installs mcp-security-auditor Audits Model Context Protocol servers for vulnerabilities, configures OAuth 2.1 flows, and designs RBAC. Useful before deploying MCP tools to production. 851installs content-curator This subagent audits Obsidian notes, spots duplicates and stale material, and suggests cleanup work. Use it when a vault needs regular content review. 846installs test-runner Runs project test suites, isolates failure causes, and suggests fixes. The agent never modifies code directly, returning a diagnostic report instead. 846installs