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/pablo-gitub/optees/agents-mdgit clone --depth 1 https://github.com/Pablo-gitub/opteesWhat 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 | $0.00754 | $0.00754 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
optees 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Agent Instructions
These instructions apply to every automated coding agent working in this repository. Keep this file concise; detailed and frequently changing project information belongs in the canonical documents linked below.
Sources of truth
Read the relevant source before making changes:
- Architecture and dependency boundaries:
docs/ARCHITECTURE.md - Test strategy, markers, and commands:
docs/TESTING.md - Versioning, packaging, and release procedure:
docs/RELEASING.md - Current implementation priorities:
docs/PROJECT_ROADMAP.mdand any feature-specific roadmap referenced from it
Do not copy large sections of these documents into agent instruction files. When implementation changes behavior, contracts, commands, architecture, supported platforms, or roadmap status, update the corresponding documentation in the same work unit. Documentation must describe shipped behavior honestly; planned functionality must remain clearly marked as planned.
Engineering workflow
- Inspect the surrounding code and existing patterns before designing a change.
- Preserve the dependency direction documented in
docs/ARCHITECTURE.md. Presentation and transport code must not become the owner of domain or solver logic. Register public solver capabilities through the existing composition and versioned-contract mechanisms. - Keep changes scoped. Do not revert, rewrite, or include unrelated user work.
- Prefer existing helpers, codecs, adapters, UI components, and i18n mechanisms over parallel implementations.
- Keep user-visible English and Italian resources synchronized. Do not hardcode translatable UI text.
- Add or update focused tests for changed behavior. Run targeted tests while
iterating, then choose broader gates according to blast radius and
docs/TESTING.md. Do not claim that tests passed when dependencies, GUI support, sockets, datasets, or platform access prevented execution. - Treat solver correctness, public JSON contracts, independent validation, update behavior, and packaging as high-risk surfaces requiring explicit regression coverage.
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 · 76 lines · 754 tokens per session scan A 31681fcbc441
optees AGENTS.md is an instructions file published in the GitHub repository Pablo-gitub/optees (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 754 tokens to every session, about $0.0038 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 instructions, from other repositories
cuopt AGENTS.md
Instructions for NVIDIA/cuopt, covering agents.md — cuopt ai agent entry point, skills directory (flat), rules, common (concepts only; no api code) and installation.
ClimaAtmos.jl AGENTS.md
Instructions for CliMA/ClimaAtmos.jl, covering climaatmos agent guide, ecosystem guidelines, repo-specific guidelines, local norms and self-correction.
ClimaAtmos.jl copilot-instructions.md
Instructions for CliMA/ClimaAtmos.jl: The authoritative agent brief for this repository is AGENTS.md at the repository root. Read it in full before suggesting code, reviewing a PR, or answering a question about this codebase, and follow it as if its contents were inlined here.
Traintools AGENTS.md
AGENTS.md instructions for AparajeetS/Traintools, covering traintools agent guide, discovery, when to suggest traintools, routing and integration rules.
cuopt copilot-instructions.md
Instructions for NVIDIA/cuopt, a project described as: GPU accelerated decision optimization.
ClimaAtmos.jl CLAUDE.md
Instructions for CliMA/ClimaAtmos.jl, a project described as: GPU-capable global atmosphere model of the CliMA Earth System Model, designed for calibration with data assimilation and machine learning.