arc AGENTS.md

A set of repository instructions for ARC, the academic-research layer of a larger system for model-led science. It describes project boundaries, research principles, evidence handling, and reproducible work.

In plain words
What is it for?
Use it when modifying ARC’s Python packages, research workflows, literature and citation tools, calculations, or documentation.
Why use it?
It gives coding agents context for the repository and helps keep research infrastructure separate from scientific judgment and unrelated packages.

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/tririver/arc/agents-md
Clone the repo
git clone --depth 1 https://github.com/tririver/arc

Made for: Codex, OpenCode.

Per session 3,116 This file is loaded in full into every session.
When invoked 3,116 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 $0.03116 $0.03116
Opus 5 $0.01558 $0.01558
Sonnet 5 $0.00623 $0.00623
Haiku 4.5 $0.00312 $0.00312

Measured 2d ago against content hash c3afc687c087, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arc 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.

AGENTS.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARC Development Guidance

ARC is the academic-research layer of the AC ecosystem. Keep its two Python packages independent of any particular agent host or checked-out Skill. Shared jobs, model, document, and proposer-reviewer infrastructure belongs to AC Foundation; learning and publication workflows belong to ALC.

Governing Philosophy: Infrastructure for Model-Led Science

ARC exists to expand the scientific ability and creativity of capable models, not to replace their scientific judgment with complicated program logic.

  • Give models better information, easier access to evidence, reliable tools, recoverable execution, and clear provenance.
  • Provide simple, repeatedly validated research practices where infrastructure is genuinely useful: independent proposer-reviewer criticism, focused literature and citation searches, reproducible calculations, explicit assumptions and uncertainty, and respectful citation of prior work.
  • Treat citation as scientific context and scholarly courtesy. Help models find and acknowledge predecessors; do not turn a bounded search result into proof of novelty or a qualification gate.
  • Leave scientific questions to model reasoning wherever correction, revision, comparison, or further evidence can resolve them. Scientific merit, relevance, novelty, simplicity, research direction, decomposition, and presentation are not validity conditions for program code.
  • Use prompts, evidence, warnings, confidence, alternatives, and reviewer feedback to improve scientific decisions. Do not encode debatable scientific taste as hard routing, deletion, disqualification, closed taxonomies, or mandatory methodological bureaucracy.
  • Reserve hard program stops for genuine system boundaries: missing authority, corrupt or unreadable durable state, invalid machine contracts that remain unusable after bounded recovery, unsafe destructive actions, or the complete absence of a usable result. Delivery failures must not erase valid scientific work.
  • Before adding complex enforcement code, ask whether it protects a necessary system invariant or instead constrains a scientific choice that a capable model should make. If the latter, provide information and feedback and trust the model.

Read the full file on GitHub · 273 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. 2d ago First seen · 273 lines · 3,116 tokens per session scan A c3afc687c087

Subscribe to this mod's changes

arc AGENTS.md is an instructions file published in the GitHub repository tririver/arc (81 stars, last pushed 7d ago), licensed MIT. It adds 3,116 tokens to every session, about $0.0156 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

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

buildNext

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

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

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

spec-kit 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 · 7,040 tokens

langchain 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