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 instructions/demml/opsml/agents-mdgit clone --depth 1 https://github.com/demml/opsmlWhat 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 | $0.05809 | $0.05809 |
| Opus 5 | $0.02905 | $0.02905 |
| Sonnet 5 | $0.01162 | $0.01162 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade C, and why
opsml AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
This repo uses [mise](https://mise.jdx.dev/) to run all dev tasks. Install with `curl https://mise.run | sh`, then `mise install` once to fetch pinned tool versions. All commands documented below are `mise run <task>`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
This repo uses [mise](https://mise.jdx.dev/) to run all dev tasks. Install with `curl https://mise.run | sh`, then `mise install` once to fetch pinned tool versions. All commands documented below are `mise run <task>`. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 469 lines · 5,809 tokens per session scan C 1c0f1b3c0ab6
opsml AGENTS.md is an instructions file published in the GitHub repository demml/opsml (40 stars, last pushed 3mo ago), with no licence file. It adds 5,809 tokens to every session, about $0.0290 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
streamlit copilot-instructions.md
Copilot instructions for streamlit/streamlit, covering streamlit repo overview, tech stack, folder structure, shell & build policy and make commands.
zenml CLAUDE.md
Claude Code instructions for zenml-io/zenml, covering zenml claude code guidelines, project structure, use zenml docs via mcp, code style & quality standards and commenting policy — explain why, not what.
zenml AGENTS.md
AGENTS.md instructions for zenml-io/zenml, covering zenml codex agent guidelines, project structure, always-loaded rules, common commands and branches, git, and prs.
mlops-python-package AGENTS.md
AGENTS.md instructions for fmind/mlops-python-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
weightslab AGENTS.md
Instructions for GrayboxTech/weightslab, covering weightslab — agent context for users & debugging, 0. how to load this guide into claude code, 1. what it is and how the pieces connect, 2. install & run (the happy path) and ... your training loop ...
streamlit python_tests.instructions.md
Instructions for streamlit/streamlit, covering python unit test guide, key principles, running tests and typing tests.