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/igpenguin/hades-gate/gemini-mdgit clone --depth 1 https://github.com/IGPenguin/hades-gateWrote 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.
[](https://agentmods.dev/instructions/igpenguin/hades-gate/gemini-md)<a href="https://agentmods.dev/instructions/igpenguin/hades-gate/gemini-md"><img src="https://agentmods.dev/badge/instructions/igpenguin/hades-gate/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00795 | $0.00795 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
hades-gate GEMINI.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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md
This file provides guidance to the Gemini CLI agent when working with this repository.
What This Is
Hades Gate is a meta-framework that separates the Architect from the Builder. In the legacy path, you (Gemini) are the Architect - you analyze intent and project context, then generate the Hexalogy proposals. The Builder (Claude) executes the chosen path.
The primary path is now a native Claude Code skill (/hades). The Gemini CLI path documented here remains functional for users without Claude Code.
Architecture
The .hades/ Folder
| File | Role | Git-tracked? |
|---|---|---|
manifesto.md |
Global coding standards for the Architect | Yes |
papyrus.md |
Template defining the 6-path proposal structure | Yes |
styx.md |
User's seeds (raw intent) - consumed by ignite |
No |
arche.md |
Project DNA snapshot generated by survey |
No |
prions.md |
Your 6-path proposals - output of ignite |
No |
erebus.env |
API keys and secrets | No |
The Ghostwire Protocol
Projects use hades link to symlink their .hades/ directory to this repository. You operate on this shared state.
Core Mandates
The Hexalogy
When generating proposals via hades ignite, always produce all six paths plus the Synthesis:
- Option A - The Spark (Fastest path): Minimal friction, immediate result.
- Option B - The Weave (Systems integration): Leveraging existing opportunities.
- Option C - The Apex (High polish): High quality, clean architecture.
- Option D - The Echo (Standard patterns): Proven, battle-tested solution.
- Option E - The Rift (Experimental): Outside-the-box or novel approach.
- Option F - The Chimera (Flashy hacks): Flashy results with a pragmatic interior.
- The Synthesis (Refined convergence): A curated selection from the strongest elements above.
State Awareness
- Arche is Ground Truth:
arche.mdcontains the project identity, file tree, and API surface. - Drift Detection: The framework warns if the project has changed since the last survey. If stale, request a re-survey via
hades survey.
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.
- 5d ago First seen · 69 lines · 795 tokens per session scan A d26cfc5be80e
hades-gate GEMINI.md is an instructions file published in the GitHub repository IGPenguin/hades-gate (1 stars, last pushed 6d ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
ccmanager CLAUDE.md
Claude Code instructions for kbwo/ccmanager, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.
claude-and-codex-website AGENTS.md
AGENTS.md instructions for justjavac/claude-and-codex-website, covering agents.md, readme.md 格式, 包月付费, 按量付费 and 规则.
ccmanager AGENTS.md
AGENTS.md instructions for kbwo/ccmanager, a project described as: Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI / OpenCode / Kimi CLI.
gemmit GEMINI.md
Instructions for tcmartin/gemmit: PROJECT TASKS I am building a lovable clone, but I want to use gemini-cli I want a function.
vibe-studio CLAUDE.md
Claude Code instructions for Xiaofan629/vibe-studio, covering vibe studio 项目指引, 一句话概览, 当前真实能力, 技术栈 and 常用命令.
niko-niko AGENTS.md
AGENTS.md instructions for dpitois/niko-niko, covering agents.md - development guidelines for agentic coding, project overview, build commands, backend (.net) and navigate to api project.