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/stepfun-ai/steptronoss/agents-mdgit clone --depth 1 https://github.com/stepfun-ai/SteptronOssWhat 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 | $0.05675 | $0.05675 |
| Opus 5 | $0.02838 | $0.02838 |
| Sonnet 5 | $0.01135 | $0.01135 |
| Haiku 4.5 | $0.00568 | $0.00568 |
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.
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.mdfor repo-wide priorsdocs/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 CLIsteptronoss/utils/comm_utils.py: Redis rendezvous, queues,LocalFuture/RemoteFuturesteptronoss/utils/dist_utils.py: broadcast / all-to-all helpers, packing helpers, balancing helperssteptronoss/utils/general.py: numeric helpers, list split/balance, RNG fork, retry, recursion helpers, git hashsteptronoss/utils/logger.py: rank-aware logging andStepWritersteptronoss/utils/metrics.py: metrics system (Metric,Avg,Percentage,Histogram,Text,GradNorm,GlobalMetrics)steptronoss/utils/optimizable.py:@optimizable(...)andset_optimization(...)steptronoss/utils/utils.py: model unwrap, param norms, memory report, layer map, IO helpers, generic loadsteptronoss/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
configurizepattern:- 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.
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.
- 3d ago First seen · 313 lines · 5,675 tokens per session scan A 72707581e13a
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.
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).
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.
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.
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.
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).
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.