coderlm

coderlm is a Codebase mapping & onboarding skill for AI agents, published by JaredStewart in the coderlm repository on GitHub. Skillspace rates coderlm B (81/100) and it passed the safety scan; the rating is based on static analysis only.

Structural codebase navigation for supported languages (Rust, Python, TypeScript, JavaScript, Go, Java, Scala, Ruby, PHP, Zig, SQL). Provides tree-sitter-backed indexing: find symbols by name, get exact function bodies, follow caller chains, discover tests. Works best combined with the Read tool: use coderlm CLI (`search`, `impl`, `callers`) to locate the right code across a codebase, then `Read` the identified files directly for full context. Use for: tracing execution paths across multiple files, answering 'what calls X', 'how does X work', 'where is X defined'. Avoid raw bash grep/find — use the coderlm `grep` command instead.

Grade
B
Quality
81 / 100
Safety
Passed
GitHub stars
294

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubJaredStewart/coderlm

Our review

Architecture
100 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More Codebase mapping & onboarding skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.