coderlm
An AI agent skill designed for complex coding tasks involving many files or large codebases, utilizing a recursive decomposition strategy and context guards to prevent information overload.
About this skill
Coderlm is an advanced AI agent skill engineered to manage large-scale coding projects. It operates by intelligently discovering relevant files using shell tools, strategically 'peeking' into their content, and recursively breaking down complex problems into smaller, manageable sub-agent tasks. This approach enables AI agents to tackle challenges that would otherwise overwhelm their context window or require intricate manual file navigation. This skill is particularly useful when dealing with projects that involve more than ten files, where the total codebase size exceeds the comfortable context window of a typical AI model, or when the task naturally benefits from a divide-and-conquer approach. It provides a structured way for agents to explore, understand, and interact with extensive codebases, making complex refactoring, bug fixing, or feature development more accessible. A key feature of coderlm is its integration with `bashrlm` context guards. These guards automatically truncate the output of verbose commands (such as `cat`, `grep`, `rg`, `jq`, `find`, `ls`, `curl`) to prevent the agent's context window from being flooded with irrelevant or excessive information. This ensures the AI agent remains focused and efficient, even in highly verbose environments, making it ideal for maintaining performance and accuracy on extensive and intricate coding assignments.
Best use case
The primary use case for coderlm is tackling complex software development tasks within large or multi-file codebases that would typically overwhelm a standard AI agent's context window. Developers, engineers, and AI agents themselves benefit most by gaining the ability to efficiently navigate, understand, and modify extensive projects without succumbing to context overflow, leading to more accurate and reliable automated coding assistance.
An AI agent skill designed for complex coding tasks involving many files or large codebases, utilizing a recursive decomposition strategy and context guards to prevent information overload.
Users can expect a more efficient and accurate completion of complex, multi-file coding tasks, without the AI agent suffering from context window overflow.
Practical example
Example input
echo "Fix type errors in src/" > task.txt && coderlm claude --prompt task.txt --allowedTools "Bash,Edit"
Example output
Files modified: src/types.ts, src/api/client.ts. All type errors resolved. Additional feedback: Checked related files and ensured type consistency throughout the project.
When to use this skill
- When a coding task involves many files (e.g., >10 files).
- When the total content of relevant files exceeds the AI agent's comfortable context size.
- When the coding task naturally benefits from a divide-and-conquer strategy.
- When working with large codebases where preventing context overflow is critical for agent performance.
When not to use this skill
- For simple tasks involving a single file or a very small, well-defined scope.
- When the task does not require complex file discovery, strategic peeking, or recursive decomposition.
- If the overhead of agent orchestration and sub-agent management is unnecessary for the task's complexity.
- For non-coding tasks that don't involve navigating file systems or code.
How coderlm Compares
| Feature / Agent | coderlm | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
An AI agent skill designed for complex coding tasks involving many files or large codebases, utilizing a recursive decomposition strategy and context guards to prevent information overload.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
## Usage ``` coderlm <agent> --prompt <file> [--max-depth N] [--allowedTools TOOLS] ``` ## Examples ```bash echo "Find all TODO comments in src/" > task.txt coderlm codex --prompt task.txt coderlm "bunx --bun @google/gemini-cli" --prompt task.txt echo "Fix type errors in src/" > task.txt coderlm claude --prompt task.txt --allowedTools "Bash,Edit" ```
Related Skills
laravel-expert
Senior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture, security, performance, and modern standards (Laravel 10/11+).
debug-nw
Debug a Nativewind v5 setup issue. Walks through common configuration problems with metro, babel, postcss, and dependencies.
Go Production Engineering
You are a Go production engineering expert. Follow this system for every Go project — from architecture decisions through production deployment. Apply phases sequentially for new projects; use individual phases as needed for existing codebases.
Database Engineering Mastery
> Complete database design, optimization, migration, and operations system. From schema design to production monitoring — covers PostgreSQL, MySQL, SQLite, and general SQL patterns.
afrexai-code-reviewer
Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.
API Documentation Generator
Generate production-ready API documentation from endpoint descriptions. Outputs OpenAPI 3.0, markdown reference docs, and SDK quickstart guides.
bili-rs
Development skill for bili-rs, a Rust CLI tool for Bilibili (B站). Use when implementing features, fixing bugs, or extending the bilibili-cli-rust codebase. Provides architecture conventions, API endpoints, coding patterns, and project-specific constraints. Triggers on tasks involving adding CLI commands, calling Bilibili APIs, handling authentication, implementing output formatting, or working with the layered cli/commands/client/payloads architecture.
Puppeteer
Automate Chrome and Chromium with Puppeteer for scraping, testing, screenshots, and browser workflows.
pharaoh
Codebase knowledge graph with 23 development workflow skills. Query architecture, dependencies, blast radius, dead code, and test coverage via MCP. Requires GitHub App installation (read-only repo access) and OAuth authentication. Connects to external MCP server at mcp.pharaoh.so.
git-commit-helper
Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.
ask-claude
Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).
bnbchain-mcp
Interact with the BNB Chain Model Context Protocol (MCP) server. Blocks, contracts, tokens, NFTs, wallet, Greenfield, and ERC-8004 agent tools. Use npx @bnb-chain/mcp@latest or read the official skill page.