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.

In plain words
What is it for?
They guide agents through the repository structure, improvement notes, command-line configuration, communication helpers, distributed computing tools, logging, and related utilities.
Why use it?
They give agents project-specific rules and shortcuts, reducing repeated exploration and helping them place changes in the right area.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/stepfun-ai/steptronoss/agents-md
Clone the repo
git clone --depth 1 https://github.com/stepfun-ai/SteptronOss

Made for: Codex, OpenCode.

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. Scan, not verified.
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 $0.05675 $0.05675
Opus 5 $0.02838 $0.02838
Sonnet 5 $0.01135 $0.01135
Haiku 4.5 $0.00568 $0.00568

Measured 3d ago against content hash 72707581e13a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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:

  1. Identify friction
  2. Extract reusable priors
  3. 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.

  1. 3d 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 (586 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 5,675 tokens to every session, about $0.0284 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens