local-llm-bridge

local-llm-bridge is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 85 tokens per session (1,168 once invoked), scanned A, original, MIT.

A bridge that sends small, bounded tasks to a Gemma language model running on your own computer. Gemma is an AI model that can work locally without sending the task to a cloud service.

In plain words
What is it for?
Use it to pass focused coding or analysis subtasks from a main agent to a local Gemma server through the llama target.
Why use it?
It provides a private, no-cloud way to delegate short tasks when the local model server is running. It is intended for quick subtask responses through the project’s task router.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the cli-agents plugin — 14 skills, 13 agents shipped together

Good fit Use it to pass focused coding or analysis subtasks from a main agent to a local Gemma server through the llama target.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/local-llm-bridge
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add richfrem/agent-plugins-skills --skill local-llm-bridge
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install cli-agents, the plugin that ships this one along with the rest of its 14 skills, 13 agents.

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 local-llm-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/local-llm-bridge/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/local-llm-bridge)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/local-llm-bridge"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/local-llm-bridge/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 local-llm-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/local-llm-bridge"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/local-llm-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00085 $0.01168
Opus 5 $0.00043 $0.00584
Sonnet 5 $0.00017 $0.00234
Haiku 4.5 $0.00009 $0.00117

Measured 5d ago against content hash 759e2193748d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

local-llm-bridge scanned grade A with 1 finding 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 5d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/kv_cache_orchestrator.py, scripts/run_agent.py, scripts/run_server.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> **Requires llama-server running on port 8089.** Check: `curl http://localhost:8089/health`
plugins/cli-agents/skills/local-llm-bridge/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity: The Local Gemma Sub-Agent Dispatcher

Dispatches bounded tasks directly to the optimized local Gemma 4 12B server at http://localhost:8089/v1/chat/completions. No routing proxy involved. Uses the run_agent.py task router with cli=llama.

[!IMPORTANT] Requires llama-server running on port 8089. Check: curl http://localhost:8089/health Start: ./run_server.sh in the local-llm-bench workspace. Thinking is disabled server-side (--reasoning off) — no special flags needed.


Why This Is Fast

The routing proxy (Mode A) carries ~29K tokens of Claude Code system prompt — at ~30 tok/s prefill that costs 60+ seconds per context boundary crossing.

This skill (Mode B) sends only the task prompt — typically 50–500 tokens. At 7+ tok/s generation on M1 Metal with a small context:

Output length Typical response time
50 tokens ~7s
100 tokens ~14s
200 tokens ~28s

Default max_tokens=120 keeps responses terse. Override via code if needed.


Orchestration Pattern: run_agent.py

python ./scripts/run_agent.py \
  <PERSONA_FILE> <INPUT_FILE> <OUTPUT_FILE> "<INSTRUCTION>" \
  --cli llama --max-tokens 120

Example — code review

python ./scripts/run_agent.py \
  agents/refactor-expert.md \
  target.py \
  review.md \
  "List the top 3 issues in this code. Be terse." \
  --cli llama

Example — summarize a diff (longer output)

python ./scripts/run_agent.py \
  /dev/null \
  changes.diff \
  summary.md \
  "Summarize this diff in 2 sentences. Focus on risk." \
  --cli llama --max-tokens 200

Example — instruction only (no input file)

python ./scripts/run_agent.py \
  /dev/null /dev/null \
  answer.md \
  "What is the capital of France? One word." \
  --cli llama --max-tokens 10

Prompt Budget Guidelines

Keep prompts lean — this is the primary performance lever:

  • Persona: 100–300 tokens (enough to set role and tone)
  • Source file: keep under 2,000 tokens where possible; trim to the relevant section
  • Instruction: 1–3 sentences; specific and bounded
  • Expected output: terse — list form, not prose paragraphs

Read the full file on GitHub · 149 lines

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. 5d ago First seen · 149 lines · 85 tokens per session scan A 759e2193748d

Subscribe to this mod's changes

local-llm-bridge is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,168 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

swarm-scripts

Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.

desplega-ai/agent-swarm · 82 tokens

semantic-creator

A workflow for turning APIs, command-line tools, or database tables into a governed semantic layer—a shared description of data and its meaning. It uses Kimball-style dimensional modeling and can produce OKF or YAML files after review.

ontology-of-everything/SemanticSkills · 68 tokens

prompt-decompiler

This skill should be used when the user says "decompile this prompt", "reverse engineer this prompt", "analyze this prompt", "break down this prompt", "what does this prompt do", "adapt this prompt for", "simplify this prompt", "split this prompt", "migrate this prompt", "why does this prompt work", "explain this…

RadOrigin-LLC/RAD-Claude-Skills · 153 tokens

model-cli-gemini

Use when invoking Google's Gemini directly through the shared Antigravity, Gemini CLI, or agent fallback chain.

tony/skills · 27 tokens

custom-model-training

Trains a custom Ideogram model on a folder of reference images, then generates a new image with that trained model to prove it works — a real end-to-end pipeline (createdataset, uploaddatasetassets, trainmodel, poll getmodel, generateimage with custommodeluri), not just an explanation of how training works. Use…

devkindhq/ideogram-ai-toolkit · 230 tokens

ideogram-prompt

Prompting technique guide for Ideogram image generation via the connected Ideogram MCP (generateimage, describeimage, remiximage, editimage). Use whenever the user wants to generate, remix, or edit an image with Ideogram — including moodboards, style-matching a reference image, extracting a visual "recipe" from…

devkindhq/ideogram-ai-toolkit · 128 tokens