TROPT: Instructions file for Codex

AGENTS.md

TROPT AGENTS.md is an instructions file for Codex, OpenCode from matanbt/TROPT. It costs 4,103 tokens per session, scanned A, original, MIT.

A repository instruction file for the TROPT machine-learning project. It tells coding agents which project guides to read, where common components live, and how to install, develop, debug, and release the software.

In plain words
What is it for?
Use it when changing TROPT recipes, losses, optimizers, models, or their combinations, and when preparing releases to PyPI, the Python package index.
Why use it?
Agents can make incorrect changes when they miss project-specific rules or architecture. These instructions provide the required starting point and route work to the right documentation.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is matanbt/TROPT's own configuration. It tells Codex and OpenCode how to work on TROPT itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TROPT configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matanbt/TROPT. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/matanbt/TROPT/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/matanbt/TROPT

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for TROPT AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/matanbt/tropt/agents-md/github.svg)](https://agentmods.dev/instructions/matanbt/tropt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/matanbt/tropt/agents-md"><img src="https://agentmods.dev/badge/instructions/matanbt/tropt/agents-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.

agentmods 80×15 button for TROPT AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/matanbt/tropt/agents-md"><img src="https://agentmods.dev/badge/instructions/matanbt/tropt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,103 This file is loaded in full into every session.
When invoked 4,103 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04103 $0.04103
Opus 5.5 $0.01641 $0.01641
Sonnet 5.5 $0.00821 $0.00821
Haiku 4.5 $0.00410 $0.00410

Measured 1mo ago against content hash 445e287ca837, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

TROPT 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 1mo 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 · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents when working with this repository. For comprehensive design philosophy see DESIGN.md; for step-by-step guides see docs/guides/.

READ FIRST for almost every TROPT task — load skills/tropt/SKILL.md. It's the user-facing companion to this dev-facing file and covers the bulk of what a contributor does day-to-day: adding a recipe, adding a loss, adding an optimizer, adding a model backend, composing custom Model + Loss + Optimizer wirings, swapping components in an existing recipe, debugging cross-cutting pitfalls (mixin mismatches, attention-loss requirements, thinking-model target alignment, black-box vs white-box loss, multi-model OOM, etc.), routing to the right guide / source file, and helping users without a local checkout. Skill loading is not automatic from <repo>/skills/ — the file must be explicitly read (this is intentional agent behavior, not a bug). Treat the skill as required reading whenever the request touches tropt/recipe_hub/, tropt/loss/, tropt/optimizer/, tropt/model/, or composition patterns. Install is just the supporting first step it also covers.

Tips

  • Keep answers short and technical; no filler.
  • If the user asks a question, answer it before making any edits.
  • Read files fully before making broad changes.
  • Prefer concise modifications — minimal changes so edits are easy to review. But if minimal changes create technical debt or unreadable code, prefer clarity.
  • Temporary scripts or markdown you create go under agent_stuff/. Don't make a mess.
  • Avoid over-commenting. Use clear names; only comment where intent isn't obvious.
  • Keep docstrings short. One or two sentences max. Only list args that aren't self-evident from name and type.
  • Docs maintenance: Don't enumerate specific classes/fields/signatures in docs — they go stale. Point to source instead (e.g., "see tropt/loss/ for the full set").

Git

  • Never commit or push unless the user explicitly asks.
  • No emojis in commits, PRs, or code.
  • Stage explicit paths only; never git add -A / git add .. Run git status before any requested commit.
  • Never run git reset --hard, git checkout ., git clean -fd, git stash, or --no-verify; they destroy work in progress.

Read the full file on GitHub · 304 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. 1mo ago Changed · +10 lines · +126 tokens per session 445e287ca837
  2. 1mo ago First seen · 294 lines · 3,977 tokens per session scan A 0a14051b75b0

Subscribe to this mod's changes

TROPT AGENTS.md is an instructions file published in the GitHub repository matanbt/TROPT (11 stars, last pushed yesterday), licensed MIT. It adds 4,103 tokens to every session, about $0.0164 per session on Opus 5.5. 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 2026-09-22.

Related

TROPT AGENTS.md compared with instructions from other repositories

TROPT AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
TROPT AGENTS.mdmatanbt/TROPTInstructions file11yesterdayMITA4,103Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode