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/salah-xd/appcn/agents-mdgit clone --depth 1 https://github.com/Salah-XD/appCNWrote 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/salah-xd/appcn/agents-md)<a href="https://agentmods.dev/instructions/salah-xd/appcn/agents-md"><img src="https://agentmods.dev/badge/instructions/salah-xd/appcn/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 | $0.01508 | $0.01508 |
| Opus 5 | $0.00754 | $0.00754 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
appCN 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude Code, Cursor, Windsurf, OpenAI Codex, Aider, …) working in the appCN repo. Read this before you touch code.
This file follows the cross-tool AGENTS.md convention — most modern agents
look for it automatically.
Read first
CLAUDE.md— architecture, monorepo map, commands, gotchas. Do not skip.DESIGN.md— the taste layer. Motion rules, the "one delight detail" requirement, the per-component file shape, the explicit what-NOT-to-do list, and the seven-step Component checklist (SOP).CONTRIBUTING.md— dev setup, PR conventions.
If you're proposing a new component, your work is invalid unless it satisfies the SOP. There are no exceptions.
Hard rules
- No new dependencies without justifying them in the PR. Especially
not icon libraries — draw glyphs from
Views/borders (seeprompt-input.tsxfor the pattern). - No
StyleSheet/ inline styles when NativeWind can express the rule. - No
AnimatedAPI. Reanimated only. Gestures viagesture-handler. - No magic durations or easings. Pull from
../lib/motion. If you find yourself hand-typing300orEasing.out(...), you're doing it wrong. - No skipping accessibility. Every interactive component needs
accessibilityRole, a label,hitSlop, and ≥ 44pt touch targets. - No light-mode-first. Design dark, then derive light.
- No
useEffectfor layout-affecting state when a derived value works.
Next.js 16 warning (apps/web only)
apps/web/ is on Next.js 16. APIs, conventions, and file structure differ
from what models were trained on. Before authoring or editing any code under
apps/web/app/, read the relevant doc in node_modules/next/dist/docs/.
Confirmed-current conventions worth flagging:
paramsis a Promise in pages and layouts — must beawaited.- Layouts are cached and do not re-render on navigation. Active-state
for nav links must live in a Client Component using
usePathname(). - See
apps/web/AGENTS.mdfor the in-app reminder.
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.
- 3d ago First seen · 127 lines · 1,508 tokens per session scan A c3f2d9d939e5
appCN AGENTS.md is an instructions file published in the GitHub repository Salah-XD/appCN (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,508 tokens to every session, about $0.0075 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
coss AGENTS.md
AGENTS.md instructions for cosscom/coss, covering agents.md and main documentation.
ui CLAUDE.md
Claude Code instructions for persianlabs/ui, covering claude.md, what this is, commands, before pushing and architecture: components exist in two places, on purpose.
ui AGENTS.md
AGENTS.md instructions for persianlabs/ui, covering this is not the next.js you know, adding a new component or utility, component and utility previews, copyable page and .md endpoint and guard script.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
MobiAI-Core CLAUDE.md
Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.