agentmods.dev

Solaris: Instructions file for Codex

AGENTS.md

Solaris AGENTS.md is an instructions file for Codex, OpenCode from Shivansh779/Solaris. It costs 2,540 tokens per session, scanned A, original, MIT.

A project instruction file for Solaris, an AI chatbot application. It records how to start the app, run its tests, manage its Python environment, and handle important user data.

In plain words
What is it for?
It is for working on Solaris, including running its web or terminal interface, installing dependencies, and running tests.
Why use it?
It gives a coding agent project-specific rules and commands, reducing the risk of changing data files or using the wrong development workflow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Shivansh779/Solaris's own configuration. It tells Codex and OpenCode how to work on Solaris itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Solaris configures →

not rated 1repo 15d ago A scan 2,540 tokens original MIT
View source ↗ Shivansh779/Solaris
Reuse

Borrowing it

Nothing to install: this file belongs to Shivansh779/Solaris. 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/Shivansh779/Solaris/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Shivansh779/Solaris

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 Solaris AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shivansh779/solaris/agents-md/github.svg)](https://agentmods.dev/instructions/shivansh779/solaris/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/shivansh779/solaris/agents-md"><img src="https://agentmods.dev/badge/instructions/shivansh779/solaris/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.

agentmods 80×15 button for Solaris AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shivansh779/solaris/agents-md"><img src="https://agentmods.dev/badge/instructions/shivansh779/solaris/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,540 This file is loaded in full into every session.
When invoked 2,540 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02540 $0.02540
Opus 5.5 $0.01016 $0.01016
Sonnet 5.5 $0.00508 $0.00508
Haiku 4.5 $0.00254 $0.00254

Measured 16d ago against content hash 5faab9b44963, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Solaris 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 16d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solaris – AI Chatbot Agent Instructions

Quick Start

python chatbot.py            # starts the web interface on 127.0.0.1 (first free port from 7900), opens the browser
python chatbot.py --terminal # legacy terminal (TUI) interface

Environment

  • Python 3.14 (.venv, managed with uv; pyproject.toml pins requires-python = ">=3.14")
  • .env required with API keys — writable from the web UI (gated by the API password)
  • config.json controls model selection and fallback chains — writable from the web UI
  • settings.json controls response style/personality — writable from the web UI
  • database.db (SQLite) holds profiles, chat history and all profile workspace data
  • All of the above are user data: never rewrite them to make a test pass

Key Commands

Task Command
Run assistant (web) python chatbot.py
Run assistant (terminal) python chatbot.py --terminal
Custom web port python chatbot.py --port 7900
Run tests pytest Test/
Offline web smoke test python Test/web_smoke.py
Install deps pip install -r requirements.txt (or uv add <pkg>)

Architecture Notes

  • Entry point: chatbot.py — launcher (port walk 7900–7909, browser open, --terminal fallback)
  • Core: core.py — session state + the whole message pipeline every front end shares
  • Web: web/app.py (pages + JSON API), web/api_workspace.py (workspace blueprint), web/access.py (profile authorization), web/jobs.py (background installs / whichllm)
  • Legacy terminal: terminal.py — the original TUI, kept working, not the default
  • Config I/O: config_io.py (JSON + _backups/), env_io.py (.env, keeps os.environ in sync)
  • Databases: main_db.py (profiles + credential hashes + migrations), history_db.py (conversations, web_log), memory_db.py (Constellation Memory), study_db.py (Study Trails), workspace_db.py (session task + checkpoint)
  • Models: chat fallback Gemini → OpenRouter → Ollama (local); summarisation OpenRouter → Ollama
  • Attachments: in-memory only (attachment.py); web uploads land in _uploads/ first
  • Voice/TTS: /api/voice (faster-whisper, lazy), /api/tts (EdgeTTS mp3 / KittenTTS wav)

Read the full file on GitHub · 147 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. 16d ago First seen · 147 lines · 2,540 tokens per session scan A 5faab9b44963

Subscribe to this mod's changes

Solaris AGENTS.md is an instructions file published in the GitHub repository Shivansh779/Solaris (1 stars, last pushed 15d ago), licensed MIT. It adds 2,540 tokens to every session, about $0.0102 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 2026-10-21.

PlanningTestingai-assistantgemini-cliopenaiopenrouter-integrationpython3voice-chat
Related

Solaris AGENTS.md compared with instructions from other repositories

Solaris AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Solaris AGENTS.mdShivansh779/SolarisInstructions file115d agoMITA2,540Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode