offload-harness AGENTS.md

Repository instructions for Offload Harness, a local-first Go system that sends short, low-judgment tasks such as summarizing, classifying, extracting, triaging, OCR, and transcription to a local Gemma model. It also documents the project structure, installation, and hardware profiles.

In plain words
What is it for?
Use it when installing, documenting, developing, or operating Offload Harness, including its command-line tool, MCP server, coding agent, and media features.
Why use it?
It gives an AI coding agent the background needed to navigate and operate the repository. Because processing stays local, the system does not call a cloud model and can defer uncertain work.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/dmmdea/offload-harness

Made for: Codex, OpenCode.

Per session 1,303 This file is loaded in full into every session.
When invoked 1,303 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01303 $0.01303
Opus 5 $0.00651 $0.00651
Sonnet 5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 2d ago against content hash 80499b8ed2c1, 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 AGENTS.md 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 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.

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.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Vendor-neutral entry point for any AI coding agent working in this repository. (Claude Code also auto-loads CLAUDE.md, which carries the same orientation in more detail.)

What this repo is

offload-harness — a local-first Go harness that delegates short-context, low-judgment work (summarize / classify / extract / triage, plus vision / OCR / transcription / media generation) to a free Gemma-4 cascade served by llama.cpp. It ships as a CLI, an MCP server (local-offload), and an optional local coding agent (local-agent). It never calls a cloud model; on low confidence it returns a structured defer so the calling agent does that task itself.

Documentation map

Detailed documentation lives in docs/. This file only routes you there.

  • docs/README.md — the index. Start here.
  • docs/systems/ — how each part of the harness works (offload pipeline, coding agent, MCP server, media generation, fleet node, installer, accelerators).
  • docs/tiers/ — one page per hardware tier (GENERATED from setup/templates/profiles.json by cmd/gentiers; run go generate ./... after changing the profile table) plus checked-in capability reports from real machines.
  • docs/flows/ — behavior that crosses systems (cascade escalation and defer, run-graph manifest satisfaction, fleet job lifecycle, zero-warm generation).
  • docs/systems/printed-clis.md — the tools/ printed CLIs: what they are, why they are separate Go modules, and the regenerate/re-vendor cycle.
  • docs/systems/opencode-integration.md — the harness inside opencode: MCP registration, rules parity, and the opencode-local-offload plugin.
  • docs/architecture/decisions/ — Architecture Decision Records. Only Accepted status is current guidance.
  • docs/glossary.md — terms with a specific meaning here (Defer, Tier, Zero-Warm, Node Manifest, …).

Read the full file on GitHub · 87 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 · 87 lines · 1,303 tokens per session scan A 80499b8ed2c1

Subscribe to this mod's changes

offload-harness AGENTS.md is an instructions file published in the GitHub repository dmmdea/offload-harness (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,303 tokens to every session, about $0.0065 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 2026-08-31.

Related

Other instructions, from other repositories

gptme AGENTS.md

AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.

gptme/gptme · 933 tokens

strix-halo-guide AGENTS.md

Instructions for hogeheer499-commits/strix-halo-guide, covering agents.md, core project lens, documentation style, do-not-invent rules and benchmark claim rules.

hogeheer499-commits/strix-halo-guide · 2,053 tokens

row-bot CLAUDE.md

Instructions for siddsachar/row-bot, a project described as: Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud…

siddsachar/row-bot · 38 tokens

maclocal-api AGENTS.md

Instructions for scouzi1966/maclocal-api, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

scouzi1966/maclocal-api · 1,269 tokens

paddler CLAUDE.md

Instructions for intentee/paddler: When working with this codebase, prioritize readability over cleverness. Ask clarifying questions before making architectural changes.

intentee/paddler · 103 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