agent-swarm: Agent for Claude Code

.claude/agents/semble-search.md

semble-search is an agent for Claude Code from desplega-ai/agent-swarm. It costs 47 tokens per session (294 once invoked), scanned A, original, MIT.

A code-search agent that finds relevant parts of a codebase from a description of what they do. A codebase is the files that make up a software project.

In plain words
What is it for?
Use it to locate implementations, understand how a feature works, find symbols, or discover related code.
Why use it?
It reduces the need to know exact filenames or search terms when exploring unfamiliar code.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is desplega-ai/agent-swarm's own configuration. It tells Claude Code how to work on agent-swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to desplega-ai/agent-swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/desplega-ai/agent-swarm/main/.claude/agents/semble-search.md
Clone the repo
git clone --depth 1 https://github.com/desplega-ai/agent-swarm

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for semble-search

README.md
[![agentmods](https://agentmods.dev/badge/agents/desplega-ai/agent-swarm/semble-search/github.svg)](https://agentmods.dev/agents/desplega-ai/agent-swarm/semble-search)
Your own site
<a href="https://agentmods.dev/agents/desplega-ai/agent-swarm/semble-search"><img src="https://agentmods.dev/badge/agents/desplega-ai/agent-swarm/semble-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for semble-search

Your own site · 80×15
<a href="https://agentmods.dev/agents/desplega-ai/agent-swarm/semble-search"><img src="https://agentmods.dev/badge/agents/desplega-ai/agent-swarm/semble-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00294
Opus 5 $0.00023 $0.00147
Sonnet 5 $0.00009 $0.00059
Haiku 4.5 $0.00005 $0.00029

Measured 9d ago against content hash 0edea5ff2344, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

semble-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/semble-search.md · 31 lines

What it actually says

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

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):

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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 31 lines · 47 tokens per session scan A 0edea5ff2344

Subscribe to this mod's changes

semble-search is an agent published in the GitHub repository desplega-ai/agent-swarm (754 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 294 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

os-architect

Front-door intake agent for Agentic OS ecosystem evolution. Classifies user intent (pattern abstraction, research application, lab setup, capability gap fill, or multi-loop orchestration), audits existing capabilities, proposes the right evolution path (orchestrate existing / update existing / create new), and…

richfrem/agent-plugins-skills · 270 tokens

exploration-cycle-orchestrator

CLI Execution Director for Path 1 (Pre-build Discovery). Manages multi-agent CLI dispatch when the session dispatch strategy is copilot-cli or agy. Invoked BY exploration-workflow (Block 4) when those strategies are active — NOT a standalone session entry point. Dispatches requirements-doc-agent…

richfrem/agent-plugins-skills · 97 tokens

wiki-init-agent

Guided initialization wizard for the Obsidian Wiki Engine. Starts with a setup mode question (wiki-only, wiki+RLM, wiki+vector, or full Super-RAG) so the user gets exactly the stack they need without requiring other plugins. Identifies raw content sources, scaffolds the wiki-root, creates…

richfrem/agent-plugins-skills · 157 tokens

vibe-orchestrator

Enterprise Systems Architect designed for Path 2: Transitioning pre-existing vibe-coded prototypes to clean production systems. It orchestrates browser audits, characterization test capture, REQS.md contracts, pure domain extraction, and vertical slice migrations. Context: User wants to evolve a rapid prototype to an…

richfrem/agent-plugins-skills · 104 tokens

improvement-intake-agent

Front-door intake agent for the Agentic OS improvement lifecycle. Runs before any skill evaluation begins. Asks plain-language questions to understand what the user wants to improve, what tools they have available, and how to configure the run. Produces a run-config.json and a session-brief.md that downstream agents…

richfrem/agent-plugins-skills · 107 tokens

os-architect-tester

Validation agent for os-architect. Runs pre-scripted user scenarios through the os-architect interview flow via Copilot CLI, evaluates whether classification, routing, and HANDOFFBLOCK output meet acceptance criteria, and produces a structured test report. Use to battle-harden os-architect after changes, or to…

richfrem/agent-plugins-skills · 176 tokens