58 tagged code search, measured the same way as everything else here.
Browse within: embeddings 18code-intelligence 11typescript 10zoekt 10
marcodavidd020/cerebro-code-memory
Agent
Use BEFORE a refactor or risky change to assess blast radius and architectural health, or to audit dead code and circular dependencies. Read-only. Answers "what breaks if I change X?", "is this safe to delete?", "where are the import cycles?", "which modules are most fragile?". Triggers (es): "qué riesgo tiene…
Agent
Auto-generated from all feature plans. Last updated: 2026-02-13.
Agent
Generate a custom checklist for the current feature based on user requirements.
Agent
Create or update the feature specification from a natural language feature description.
Agent
Specialist reviewer for CodeMeridian-assisted architecture checks, impact analysis, tests, async, logging, nullability, and analyzer risks.
Agent
Specialist agent for gathering minimal CodeMeridian graph context before code changes.
Agent
Use this agent to scan a cloned code repository and generate per-function/class markdown documentation. Invoke during rk-create (full initial index) or rk-update (incremental processing of changed files). The agent enforces documentation granularity rules (one doc per function, split large classes by method) and…
Agent
Use this agent to search a codebase knowledge base via 4-layer progressive matching (alias lookup → semantic index match → verify in cached doc → source-code fallback). The agent updates aliases on successful matches so future queries resolve faster. Invoke during rk-search for any natural-language query about an…
Agent Claude Code
Independent semantic review of a Cartograph Rust/PostgreSQL diff before merge or release. Read-only; checks correctness, bounds, concurrency, migration safety, agent evidence quality, and gate alignment.
WangChangxin0809/repo-agent-harness
Agent
Answers "where does X happen, and what would break if I changed it" for a repository, by querying the repo graph and reading what it points at. Use when the answer needs more than three files read — it returns a conclusion with citations instead of file dumps.
Agent
Use this agent when the user needs codebase exploration by behavior instead of exact-string lookup. Examples.
Agent Claude Code
Reads one repository and returns its five knowledge documents as text. Read-only by construction — it cannot write files. Use it for /study, /refresh, and any time a repo needs to be understood from scratch.