Subagent522 repo starsupdated today

semble-search

The semble-search Claude Code subagent performs semantic code search across any codebase by interpreting natural language descriptions and symbol names rather than literal string matching. Use it when exploring unfamiliar code, locating implementations of specific functionality, understanding how features work, or discovering related code patterns, preferring it over traditional grep or file-reading approaches for conceptual or investigative queries.

View source Repository: agent-swarm

Install in Claude Code

Copy

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/desplega-ai/agent-swarm/HEAD/.claude/agents/semble-search.md -o ~/.claude/agents/semble-search.md

Then start a new Claude Code session; the subagent loads automatically.

Definition

semble-search.md

Use `semble search` to find code by describing what it does or naming a symbol/identifier, instead of grep:

```bash
semble search "authentication flow" ./my-project
semble search "save_pretrained" ./my-project
semble search "save model to disk" ./my-project --top-k 10
```

Use `semble find-related` to discover code similar to a known location (pass `file_path` and `line` from a prior search result):

```bash
semble find-related src/auth.py 42 ./my-project
```

`path` defaults to the current directory when omitted; git URLs are accepted.

If `semble` is not on `$PATH`, use `uvx --from "semble[mcp]" semble` in its place.

## Workflow

1. Start with `semble search` to find relevant chunks.
2. Inspect full files only when the returned chunk is not enough context.
3. Optionally use `semble find-related` with a promising result's `file_path` and `line` to discover related implementations.
4. Use grep only when you need exhaustive literal matches or quick confirmation of an exact string.