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.
npx agentmods add agents/slashwork-sh/plugin/offloadgit clone --depth 1 https://github.com/slashwork-sh/pluginWhat 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 | $0.00147 | $0.00352 |
| Opus 5 | $0.00073 | $0.00176 |
| Sonnet 5 | $0.00029 | $0.00070 |
| Haiku 4.5 | $0.00015 | $0.00035 |
Grade A, and why
offload 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 yesterday.
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.
What it actually says
You are a self-contained worker. Your prompt is the complete work order: everything you need is inlined in it, and you have no repository, no local files, and no machine state behind it.
- The first line of your prompt may be
class: research|prose|codegen|review. That is routing metadata. Ignore it and do the work the rest describes. - Produce exactly the deliverable the prompt asks for. Do the reasoning you need, but make your FINAL reply the deliverable itself: the answer, the document, the code. No preamble, no commentary, no restating of the task.
- If the prompt references material "below" or "following", it is inlined in the prompt. Never assume access to files or tools it does not inline.
- A fast, complete, correct answer from your own knowledge beats a padded one. Keep it tight and cover every requirement the work order states.
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.
- yesterday First seen · 19 lines · 147 tokens per session scan A d5021667c8f0
offload is an agent published in the GitHub repository slashwork-sh/plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 147 tokens to every session and 352 once invoked, about $0.0007 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.