What is SteptronOss AGENTS.md?

Repository instructions for agents working on StepTronOSS, a software project with code for models, data, experiments, optimization, and text processing. They describe the project's layout and common utilities.

They guide agents through the repository structure, improvement notes, command-line configuration, communication helpers, distributed computing tools, logging, and related utilities.

They give agents project-specific rules and shortcuts, reducing repeated exploration and helping them place changes in the right area.

How stepfun-ai/SteptronOss configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to stepfun-ai/SteptronOss. 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/stepfun-ai/SteptronOss/dev/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/stepfun-ai/SteptronOss

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/stepfun-ai/steptronoss/agents-md/github.svg)](https://agentmods.dev/instructions/stepfun-ai/steptronoss/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stepfun-ai/steptronoss/agents-md"><img src="https://agentmods.dev/badge/instructions/stepfun-ai/steptronoss/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/stepfun-ai/steptronoss/agents-md"><img src="https://agentmods.dev/badge/instructions/stepfun-ai/steptronoss/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,675 This file is loaded in full into every session.

When invoked 5,675 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.

Model	Per session	Once invoked
Fable 5.1	$0.05675	$0.05675
Opus 5.5	$0.02270	$0.02270
Sonnet 5.5	$0.01135	$0.01135
Haiku 4.5	$0.00568	$0.00568

Measured 2mo ago against content hash 72707581e13a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SteptronOss 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 2mo 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 · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StepTronOSS AGENTS

This file stores repo-specific priors for future agents. Keep it short, practical, and biased toward things that save repeated exploration.

1. Working Rules

Self-Improvement Loop

Do an improve pass for key tasks:

new environment
new task type
new project area
high risk / high cost work
collaboration / handoff work

Improve pass:

Identify friction
Extract reusable priors
Write them down in:
- AGENTS.md for repo-wide priors
- docs/ for process / runbook details

2. Repo Layout

Core package: steptronoss/
- core, model, data, exp, optimizer, generation, tokenizer, utils, checkpointing
Experiments: playground/
Tests: tests/
Docs: docs/

Utilities overview

steptronoss/utils/arguments.py: config overrides from CLI
steptronoss/utils/comm_utils.py: Redis rendezvous, queues, LocalFuture / RemoteFuture
steptronoss/utils/dist_utils.py: broadcast / all-to-all helpers, packing helpers, balancing helpers
steptronoss/utils/general.py: numeric helpers, list split/balance, RNG fork, retry, recursion helpers, git hash
steptronoss/utils/logger.py: rank-aware logging and StepWriter
steptronoss/utils/metrics.py: metrics system (Metric, Avg, Percentage, Histogram, Text, GradNorm, GlobalMetrics)
steptronoss/utils/optimizable.py: @optimizable(...) and set_optimization(...)
steptronoss/utils/utils.py: model unwrap, param norms, memory report, layer map, IO helpers, generic load
steptronoss/utils/weight_loader.py: HF safetensors mapping / merge

3. Code Style

Config style

Config class fields should include a short triple-quoted docstring immediately after the attribute definition.
Follow the configurize pattern:
- class attrs declare sub-config types
- instance __init__ sets concrete values
- use Ref("..path") for cross-node linkage
- configs expose build() / build_*, sanity_check(), to_dict()
Only Ref(...) the exact parameter needed, not whole config objects.

Read the full file on GitHub · 313 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.

2mo ago First seen · 313 lines · 5,675 tokens per session scan A 72707581e13a

Subscribe to this mod's changes

SteptronOss AGENTS.md is an instructions file published in the GitHub repository stepfun-ai/SteptronOss (589 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,675 tokens to every session, about $0.0227 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 2026-08-30.

SteptronOss AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SteptronOss AGENTS.mdstepfun-ai/SteptronOss	Instructions file	589	2mo ago	Apache-2.0	A	5,675	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

SteptronOss: Instructions file for Codex