offload-harness CLAUDE.md

A local-first Go system that sends routine tasks such as summarising, classifying, extracting, triaging, image reading, speech-to-text, and media generation to local Gemma models. It provides a command-line tool, an MCP server, and an optional coding-agent loop.

In plain words
What is it for?
Use it to run local text, image, audio, and media-processing tasks, or to operate a local coding agent through one-shot, queue, or server modes.
Why use it?
It handles routine work on the local machine without sending it to the cloud. When the local model is unsure, it returns a structured defer result instead of silently escalating.

Instructions file

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.

agentmods
npx agentmods add instructions/dmmdea/offload-harness/claude-md
Clone the repo
git clone --depth 1 https://github.com/dmmdea/offload-harness
Per session 3,056 This file is loaded in full into every session.
When invoked 3,056 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.03056 $0.03056
Opus 5 $0.01528 $0.01528
Sonnet 5 $0.00611 $0.00611
Haiku 4.5 $0.00306 $0.00306

Measured 2d ago against content hash fa264cb3f128, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

offload-harness CLAUDE.md 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 2d 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.

Makes network callslowCapability

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

| `local-agent` | Coding-agent loop; one-shot, `--queue`, or `--serve` | `127.0.0.1:18800` (serve, OPTIONAL, OFF by default) | shares harness config; flags | `curl 127.0.0.1:18800/v1/models` |
CLAUDE.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — agent orientation map for offload-harness

Local-first Go harness that offloads grunt work (summarize/classify/extract/triage + vision/OCR/STT/ media-gen) to a free Gemma-4 cascade on llama.cpp. Ships as a CLI, an MCP server (local-offload), and an optional local coding agent (local-agent). The cascade never calls cloud; on low confidence it returns a structured defer and the caller does the task. (offload_nim is the one remote surface — an explicit, caller-invoked side channel that nothing escalates or falls back into.) Every command below was executed successfully while writing this file.

Components & ports

Binary / service Role Port Config Health check
llama-swap (fronts llama.cpp) Serves the model tiers 127.0.0.1:11436 $OFFLOAD_HOME\llama-swap.yaml local-offload doctorhealth: OK
local-offload Offload CLI + MCP (stdio) — (talks to :11436) ~/.local-offload/config.json local-offload doctor
local-agent Coding-agent loop; one-shot, --queue, or --serve 127.0.0.1:18800 (serve, OPTIONAL, OFF by default) shares harness config; flags curl 127.0.0.1:18800/v1/models
OpenWebUI Chat GUI over the agent (OPTIONAL) 127.0.0.1:8081 env in scripts/openwebui-stack.sh curl 127.0.0.1:8081/health

The --serve endpoint is unauthenticated and drives write/GitHub tools → loopback-only; --listen-trusted-network is required to bind beyond loopback (loud warning).

Model tiers (served by llama-swap on :11436)

Alias Config key Role
gemma4-e2b triage_model Fast entry tier — triage / classify.
offload-e4b (alias gemma4-e4b) model Workhorse — summarize / extract; default agent planner.
gemma4-26b-a4b escalation_model / reasoning_model MoE tier tried before deferring.
embeddinggemma (memory stack) Embeddings.
qwen3vl-4b, whisper-stt, whisper-stt-hq vision_model / stt_model[_hq] Vision + speech. All opt-in and DERIVED: a tier declares a media_seats entry, which renders the llama-swap seat and writes the binding together. No seat, no binding, route defers.

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 3,056 tokens per session scan A fa264cb3f128

Subscribe to this mod's changes

offload-harness CLAUDE.md is an instructions file published in the GitHub repository dmmdea/offload-harness (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,056 tokens to every session, about $0.0153 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 2026-08-31.

Related

Other instructions, from other repositories

maclocal-api CLAUDE.md

Instructions for scouzi1966/maclocal-api, covering claude code reference for maclocal api, project overview, project structure, provider source ownership and dwarfstar dependency boundary.

scouzi1966/maclocal-api · 4,520 tokens

docmind-ai-llm AGENTS.md

Instructions for BjornMelin/docmind-ai-llm, covering docmind ai: agent instructions, purpose, layout, quick commands with uv and non-negotiables for ci and security.

BjornMelin/docmind-ai-llm · 5,757 tokens

Bonsai-demo AGENTS.md

Instructions for PrismML-Eng/Bonsai-demo, covering agent guide — tuning the bonsai demo, why the 27b models (what to show off), the models, knobs that matter (27b) and adding mcp servers.

PrismML-Eng/Bonsai-demo · 4,251 tokens

James-RAG-Evol CLAUDE.md

Instructions for Hashevolution/James-RAG-Evol, covering james — session briefing for claude code, what james is, where we are right now, critical rules for this session and where to look next.

Hashevolution/James-RAG-Evol · 8,912 tokens

Local-Model Harness Tuning Workflow

Pragmatic playbook for running the harness against local LLMs (2B-13B class) and iterating until numbers improve. Captures gotchas that bite every time.

raydeStar/sir-thaddeus · 4,932 tokens

myrmion-graphrag CLAUDE.md

Claude Code instructions for e2its/myrmion-graphrag, covering claude.md, qué es esto, herramientas del servidor myrmion-graphrag (documentos), herramientas del servidor myrmion-codebase (código) and mantenimiento obligatorio del codebaseinventory.

e2its/myrmion-graphrag · 1,198 tokens