[feat] Evaluate rlmgrep for terraphim-ai codebase search

Context

rlmgrep (github.com/halfprice06/rlmgrep) is a grep-shaped CLI search tool powered by DSPy's RLM (Refined Language Model). It accepts natural-language queries and returns matches in grep-like format, with full visibility into the RLM's reasoning loop (via rlmgrep -v).

Relevant signal: Alex has liked and bookmarked the rlmgrep launch tweet, indicating strong interest in RLM-based search for codebases.

Problem Statement

Current codebase search tools (grep, ripgrep, gtr for issue triage) operate on text/regex patterns. RLM-based search could:

1. Answer natural-language questions about the codebase — Where is retry/backoff configured and what are the defaults? — and return the actual source lines in grep format
2. Understand semantic intent — e.g. find the error handling around the gitea API calls without needing to know the exact function names
3. Expose the RLM reasoning trace — rlmgrep -v shows iteration-by-iteration reasoning, which is audit-worthy for AI-assisted toolchains

Evaluation Criteria

• Install rlmgrep: uv tool install --python 3.11 rlmgrep
• Run against terraphim-ai Rust codebase — test semantic queries about error handling, executor selection, RLM hook invocation
• Run against terraphim/terraphim-skills skill definitions — test natural-language skill discovery
• Compare output quality vs grep -r and gtr for the same queries
• Evaluate --answer mode for generating code answers grounded in actual source
• Assess whether the verbose RLM trace (-v) is useful for agent audit trails
• Document findings in .docs/rlmgrep-evaluation.md

rlmgrep Key Features to Test

References

• rlmgrep repo: github.com/halfprice06/rlmgrep
• Author: @gooby_esq (Daniel Price)
• Install: uv tool install --python 3.11 rlmgrep
• RLM concept: DSPy RLM — LLM that generates code to fetch information, then reasons over results before submitting

Labels

feature/evaluation, AI/RLM, good-first-issue

Priority

P2 — informational/value assessment before committing any integration work.

Install rlmgrep with uv tool install --python 3.11 rlmgrep, then run the listed semantic queries against the terraphim-ai Rust codebase and terraphim/terraphim-skills. Compare results with grep -r and gtr, test the listed modes and providers, and record whether the criteria are met in .docs/rlmgrep-evaluation.md.