Semble is a code-search library that indexes repositories and returns relevant code snippets for natural-language questions, giving coding agents focused context without reading whole files. Developers use it through an MCP server, command-line integration, or dedicated sub-agent on local CPU-based setups. Catalogue add-ons provide agents that use Semble for repository search.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MinishLab/semblenpx agentmods add agents/minishlab/semble/commandcodeWrote 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.
[](https://agentmods.dev/agents/minishlab/semble/commandcode)<a href="https://agentmods.dev/agents/minishlab/semble/commandcode"><img src="https://agentmods.dev/badge/agents/minishlab/semble/commandcode/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.
<a href="https://agentmods.dev/agents/minishlab/semble/commandcode"><img src="https://agentmods.dev/badge/agents/minishlab/semble/commandcode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00567 |
| Opus 5.5 | $0.00018 | $0.00227 |
| Sonnet 5.5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
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 1mo 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.
This is a copy
86% identical to semble-search — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 --max-snippet-lines 10 # first 10 lines only, concise
semble search "save_pretrained" ./my-project # full chunk content
semble search "save model to disk" ./my-project --top-k 10 # more results
Results are cached automatically on first run and invalidated when files change.
Use --content docs to search documentation and prose, --content config for config files (yaml, toml, etc.), or --content all to search code, docs, and config:
semble search "deployment guide" ./my-project --content docs
semble search "database host port" ./my-project --content config
semble search "authentication" ./my-project --content all
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. Pass several paths or URLs to search related repos together, e.g. when this project calls a service defined in a sibling repo. Result paths are then prefixed with the repo name and the output includes a repos map from prefix to location:
semble search "invoice endpoint" ./service-a ../service-b
If semble is not on $PATH, use uvx --from "semble[mcp]" semble in its place.
Workflow
- Start with
semble searchto find relevant chunks. The index is built and cached automatically. - Use
--content docsfor documentation,--content configfor config files, or--content allfor everything. - Navigate directly to the returned file and line. Do not re-search or grep for the same content.
- Optionally use
semble find-relatedwith a promising result'sfile_pathandlineto discover related implementations. - If the answer may live in a dependent or sibling repo, pass all relevant repo paths to one
semble searchcall. - Use grep only when you need every occurrence of a literal string across the whole repo (e.g., all callers of a renamed function).
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.
- 1mo ago Changed · +5 lines 6c0b3eef7403
- 1mo ago First seen · 42 lines · 44 tokens per session scan A d7746f585d74
semble-search is an agent published in the GitHub repository MinishLab/semble (6,210 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 567 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to semble-search, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
feedback-triage
Turns one narrated screen recording (processed by the talkthrough MCP server) into precise, evidence-backed findings plus a numbered confirm digest. Never files issues itself — it produces the findings JSON; filing happens only after the recording author approves.
code-explorer
Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question requires understanding how multiple files connect.
ops-auditor
Audit the aurora-agent control plane's operational evidence — snapshots, capability gates, domain activity, and the recovery matrix. Delegate to this agent when asked whether the aurora backend is healthy, what the gates say, what would survive a restart, or to summarize operational posture. It reports evidence…
stata-debugger
Stata error diagnosis and debugging agent. Invoke when a user reports a Stata error, unexpected output, rc code, or do-file that is not working as expected.
spark-performance
Diagnose PySpark performance bottlenecks, distributed execution pitfalls, and suggest Spark-native rewrites and safer distributed patterns (incl. mapInPandas guidance).
Demonstrate
Agent for demonstrating VS Code features.