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/ces-ltd/titanx/agents-mdgit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote 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/ces-ltd/titanx/agents-md)<a href="https://agentmods.dev/instructions/ces-ltd/titanx/agents-md"><img src="https://agentmods.dev/badge/instructions/ces-ltd/titanx/agents-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 | $0.01680 | $0.01680 |
| Opus 5 | $0.00840 | $0.00840 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
TitanX 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AionUi - Project Guide
Code Conventions
File & Directory Structure
- Directory size limit: A single directory must not exceed 10 direct children (files + subdirectories). Split by responsibility when approaching this limit.
See docs/conventions/file-structure.md for complete rules on directory naming, page module layout, and shared vs private code placement. Agents working in this repository must also read and follow the architecture skill (.claude/skills/architecture/SKILL.md) when creating files, modules, or making structure decisions.
Naming
- Components: PascalCase (
Button.tsx,Modal.tsx) - Utilities: camelCase (
formatDate.ts) - Hooks: camelCase with
useprefix (useTheme.ts) - Constants files: camelCase (
constants.ts) — values inside use UPPER_SNAKE_CASE - Type files: camelCase (
types.ts) - Style files: kebab-case or
ComponentName.module.css - Unused params: prefix with
_
UI Library & Icons
- Components:
@arco-design/web-react— no raw interactive HTML (<button>,<input>,<select>, etc.) - Icons:
@icon-park/react
CSS
- Prefer UnoCSS utility classes; complex styles use CSS Modules (
ComponentName.module.css) - Colors must use semantic tokens from
uno.config.tsor CSS variables — no hardcoded values - Arco overrides go in the component's CSS Module via
:global()— no global override files - Global styles only in
src/renderer/styles/
See docs/conventions/file-structure.md for full CSS and UI library rules.
TypeScript
- Strict mode enabled — no
any, no implicit returns - Use path aliases:
@/*,@process/*,@renderer/*,@worker/* - Prefer
typeoverinterface(per Oxlint config) - English for code comments; JSDoc for public functions
Architecture
Three process types — never mix their APIs:
src/process/— main process, no DOM APIssrc/renderer/— renderer, no Node.js APIssrc/process/worker/— fork workers, no Electron APIs
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.
- 4d ago First seen · 133 lines · 1,680 tokens per session scan A 5da25266b54a
TitanX AGENTS.md is an instructions file published in the GitHub repository CES-Ltd/TitanX (47 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,680 tokens to every session, about $0.0084 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.
Other instructions, from other repositories
wayland CLAUDE.md
Claude Code instructions for FerroxLabs/wayland, a project described as: Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
template-repo copilot-instructions.md
Instructions for AndrewAltimit/template-repo, covering project context for ai code review, project overview, ai agent ecosystem, core design principles and 1. container-first philosophy.
psyche-build AGENTS.md
Instructions for OpenCoven/psyche-build, covering psyche build agent guide, repository role, planning and evidence contract, canonical routing and deterministic entrypoints.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
systemprompt-template CLAUDE.md
Claude Code instructions for systempromptio/systemprompt-template, covering claude.md, enterprise demo, branching & release flow, building against local core (next tracks next) and quick start.
comis AGENTS.md
Instructions for comisai/comis, covering agents.md — comis engineering protocol, 1) architecture, package map, 1.1 generic agent runtime invariant and 2) engineering principles (normative).