sophotron AGENTS.md

sophotron AGENTS.md is an instructions file for Codex, OpenCode from rookslog/sophotron. It costs 170 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on the Sophotron project. They explain which project guides to read, how to verify changes, and rules for reporting results.

In plain words
What is it for?
Use them when modifying Sophotron, especially to follow its architecture, contribution process, writing rules, testing commands, and error-handling requirements.
Why use it?
They give an agent the project’s requirements before it edits code, helping avoid incorrect changes and misleading reports.

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

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 sophotron AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rookslog/sophotron/agents-md.svg)](https://agentmods.dev/instructions/rookslog/sophotron/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rookslog/sophotron/agents-md"><img src="https://agentmods.dev/badge/instructions/rookslog/sophotron/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 This file is loaded in full into every session.
When invoked 170 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 $0.00170 $0.00170
Opus 5 $0.00085 $0.00085
Sonnet 5 $0.00034 $0.00034
Haiku 4.5 $0.00017 $0.00017

Measured 3d ago against content hash 314a77d4255f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sophotron 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 · 18 lines

What it actually says

Agent instructions

The operational guide for this repo lives in CLAUDE.md — architecture, module conventions, correctness contracts, and the verification commands that define "done". It is harness-agnostic despite the name; read it in full before editing anything.

Also binding:

  • CONTRIBUTING.md — workflow, review process, and the claims discipline for PR descriptions (state only what was actually run).
  • docs/style-guide.md — for any public-facing prose you write, including PR descriptions.

Two rules worth repeating because violations are silent: stdout is the MCP transport (log to stderr only), and a transient upstream failure (429/5xx) must never be reported as a genuine empty result.

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 · 18 lines · 170 tokens per session scan A 314a77d4255f

Subscribe to this mod's changes

sophotron AGENTS.md is an instructions file published in the GitHub repository rookslog/sophotron (0 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session, about $0.0009 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 2026-08-31.