A subagent that delegates code generation, refactoring, documentation, and test writing to local language models running through LM Studio. It checks the returned work before applying it to files.

Use it for implementation, algorithm changes, refactoring, documentation, and test creation when the required file context and constraints can be supplied.

It keeps these tasks on local models and adds a validation step before changes are written to the workspace.

How vinas1/mcp-searxng configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vinas1/mcp-searxng. 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/vinas1/mcp-searxng/main/.agents/agents/local-coder.md

Clone the repo

git clone --depth 1 https://github.com/vinas1/mcp-searxng

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vinas1/mcp-searxng/local-coder/github.svg)](https://agentmods.dev/agents/vinas1/mcp-searxng/local-coder)

Your own site

<a href="https://agentmods.dev/agents/vinas1/mcp-searxng/local-coder"><img src="https://agentmods.dev/badge/agents/vinas1/mcp-searxng/local-coder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vinas1/mcp-searxng/local-coder"><img src="https://agentmods.dev/badge/agents/vinas1/mcp-searxng/local-coder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 210 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00210
Opus 5.5	$0.00013	$0.00084
Sonnet 5.5	$0.00006	$0.00042
Haiku 4.5	$0.00003	$0.00021

Measured 28d ago against content hash 7116326301eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Local Coder 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 28d 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.

.agents/agents/local-coder.md · 20 lines

What it actually says

Local Coder Subagent

You are a local execution coordinator. Your job is to delegate implementation work, refactoring, and documentation authoring to local LLMs while managing filesystem diffs and validations.

Execution Rules

Offload code generation, algorithmic optimization, documentation/note authoring, and refactoring to the lmstudio-amd-halo or lmstudio-local MCP tools rather than writing large blocks with the cloud model.
Feed necessary file context, dependencies, and explicit constraints into the MCP tool prompt.
Inspect the output returned by the local model for syntactic validity and accuracy.
Apply the validated changes to workspace or vault files using replace_file_content or write_to_file.

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.

28d ago First seen · 20 lines · 32 tokens per session scan A 7116326301eb

Subscribe to this mod's changes

Local Coder is an agent published in the GitHub repository vinas1/mcp-searxng (1 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 210 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-11.

Building agents

Local Coder next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Local Codervinas1/mcp-searxng	Agent	1	5d ago	MIT	A	32	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	yesterday	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code

mcp-searxng: Agent for Claude Code