Borrowing it
Nothing to install: this file belongs to dmmdea/offload-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dmmdea/offload-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/dmmdea/offload-harnessWrote 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/instructions/dmmdea/offload-harness/claude-md)<a href="https://agentmods.dev/instructions/dmmdea/offload-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/dmmdea/offload-harness/claude-md/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/instructions/dmmdea/offload-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/dmmdea/offload-harness/claude-md.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 | $0.03963 | $0.03963 |
| Opus 5.5 | $0.01585 | $0.01585 |
| Sonnet 5.5 | $0.00793 | $0.00793 |
| Haiku 4.5 | $0.00396 | $0.00396 |
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 today.
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` | How it starts
The opening of the file, as written. The whole thing — 174 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 doctor → health: 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. |
embeddinggemma2 |
(memory stack) | EmbeddingGemma-2; opt-in per tier (include_embeddinggemma2), with its multimodal projector on the memory authority's tier and text-only (embeddinggemma2_projector: false, no --mmproj) on replicas; no aliases, beside embeddinggemma. |
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. |
timestral-209m (aliases forecast, timestral) |
forecast_model |
Time-series forecasting (offload_forecast; Timestral-209M, torch, fp32). A llama-swap media seat of kind forecast, DERIVED like the vision and speech seats: resident on tiers with cards of 16 GB or more, swappable on ampere-8/blackwell-8/ampere-6, unseated elsewhere (those boxes forward to a fleet node). Runtime placed by local-offload install forecast. |
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.
- today Changed · +35 tokens per session 6eb41bfcff49
- 4d ago Changed · +1 lines · +129 tokens per session ab67096903b0
- 10d ago Changed · +25 tokens per session 4bcf74002af1
- 15d ago Changed · +2 lines · +131 tokens per session b33f09e35e14
- 19d ago Changed · +1 lines · +81 tokens per session 781a9948fc13
- 25d ago Changed · +12 tokens per session 0f5169b61cce
- 27d ago Changed · +2 lines · +54 tokens per session cd1bfa6d7255
- 28d ago Changed · +8 tokens per session bfb8d42ccc75
- 29d ago Changed · +1 lines · +86 tokens per session fcf2356c14d2
- 1mo ago First seen · 167 lines · 3,402 tokens per session scan A bb32309e5e53
offload-harness CLAUDE.md is an instructions file published in the GitHub repository dmmdea/offload-harness (4 stars, last pushed today), licensed Apache-2.0. It adds 3,963 tokens to every session, about $0.0159 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.