omnissiah: Instructions file for Codex

AGENTS.md

omnissiah AGENTS.md is an instructions file for Codex, OpenCode from jwmarcus/omnissiah. It costs 1,079 tokens per session, scanned A, original, MIT.

Project instructions for Omnissiah, a generator that creates personalized repositories for bounded MCP assistants. They explain the project’s architecture, templates, command-line interface, and safe ways to change it.

In plain words
What is it for?
Use them when modifying Omnissiah’s generator, templates, rendering code, or generated repository structure.
Why use it?
They give a coding assistant the project context needed to edit the generator without breaking its output contract.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is jwmarcus/omnissiah's own configuration. It tells Codex and OpenCode how to work on omnissiah 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 omnissiah configures →

Reuse

Borrowing it

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

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 omnissiah AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jwmarcus/omnissiah/agents-md"><img src="https://agentmods.dev/badge/instructions/jwmarcus/omnissiah/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,079 This file is loaded in full into every session.
When invoked 1,079 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 $0.01079 $0.01079
Opus 5.5 $0.00432 $0.00432
Sonnet 5.5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured 2mo ago against content hash e05e46618113, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

omnissiah 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 2mo 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omnissiah Project Instructions

This file orients an AI coding assistant opened in this folder. It is about changing the generator itself. The generated project contract comes from templates/AGENTS.md.tmpl; templates/CLAUDE.md.tmpl is its Claude Code adapter.

What this project is

Omnissiah is a generator. Someone clones it, runs a CLI, answers a few questions, and gets a personalized repo for their own bounded MCP assistant: a governance layer (operating contract, assistant profile, host config) plus a runnable, provider-agnostic MCP server skeleton. It exists to hand other people the strengths of a private assistant called Wintermute without its private contents: a concrete operating contract, a scoped and auditable tool boundary, and a "safe but permissive" set of defaults.

The full design contract is docs/dev/BUILD-SPEC.md. Read it before changing behavior. It defines the template variables, the output layout, the file manifest, and the CLI interface.

Architecture

  • omnissiah/ is the generator's own code (stdlib only, no third-party deps):
    • omnissiah/render.py: the rendering engine. Walks templates/, evaluates conditionals, substitutes tokens, strips .tmpl, and renames the pkg/ directory to the assistant slug.
    • omnissiah/cli.py: argparse CLI. Interactive prompts, --answers <json>, --defaults, --output, --force. Derives the slug and stamps the date.
    • pyproject.toml (root): console script omnissiah = "omnissiah.cli:main".
  • templates/ is the corpus that gets rendered into a friend's repo. Every file ends in .tmpl. The templates/pkg/ tree becomes the generated Python package (renamed to the assistant slug). The crown jewel is templates/OPERATING-CONTRACT.md.tmpl.
  • docs/DEFAULTS-RATIONALE.md explains why each safe-but-permissive default is the recommended middle ground. docs/dev/BUILD-SPEC.md is the internal spec.

Template syntax

  • Tokens: {{VAR}} (double braces). Variable names are fixed in the spec; do not invent new ones without updating the spec, the CLI context, and the rationale.
  • Conditionals: {{#IF VAR}} ... {{/IF}}, both own-line and inline. They are evaluated before token substitution, so {{ASSISTANT_SLUG}} inside an {{#IF}} block renders fine. Wrap whole statements or whole lines so that any on/off combination still renders valid Python and clean Markdown.

Read the full file on GitHub · 85 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. 2mo ago First seen · 85 lines · 1,079 tokens per session scan A e05e46618113

Subscribe to this mod's changes

omnissiah AGENTS.md is an instructions file published in the GitHub repository jwmarcus/omnissiah (6 stars, last pushed 3mo ago), licensed MIT. It adds 1,079 tokens to every session, about $0.0043 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 2026-08-31.

Related

omnissiah AGENTS.md compared with instructions from other repositories

omnissiah AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
omnissiah AGENTS.mdjwmarcus/omnissiahInstructions file63mo agoMITA1,079Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot