Borrowing it
Nothing to install: this file belongs to tonyghiani/ai-essentials. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tonyghiani/ai-essentials/main/AGENTS.mdgit clone --depth 1 https://github.com/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/agents-md)<a href="https://agentmods.dev/instructions/tonyghiani/ai-essentials/agents-md"><img src="https://agentmods.dev/badge/instructions/tonyghiani/ai-essentials/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.
<a href="https://agentmods.dev/instructions/tonyghiani/ai-essentials/agents-md"><img src="https://agentmods.dev/badge/instructions/tonyghiani/ai-essentials/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02979 | $0.02979 |
| Opus 5.5 | $0.01192 | $0.01192 |
| Sonnet 5.5 | $0.00596 | $0.00596 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade A, and why
ai-essentials 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 6d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-essentials
Agent configuration for this repository. Install globally via symlinks (see README.md) or reference these paths when working inside this repo.
Always apply
- rules/no-ai-prose.mdc
- rules/numbered-replies.mdc
- rules/no-ai-attribution.mdc: remote actions carry the user's name only
- rules/verification-evidence.mdc: report commands and output, not assertions
- rules/test-value.mdc: tests only for behaviour worth protecting; CI runs cost money
For Claude Code these two, plus verification discipline and a compact TS/React invariants block, are assembled in claude/CLAUDE.md.
Code style (file-scoped)
Each rule activates on its own globs. Read the one matching the file you are editing.
| Editing | Rule |
|---|---|
any .ts / .tsx |
rules/typescript-style.mdc |
| adding files, folders, or imports | rules/project-structure.mdc |
| components and hooks | rules/react-components.mdc |
| server, services, routes | rules/node-api-patterns.mdc |
*.test.ts(x) / *.spec.ts(x) |
rules/testing-style.mdc |
These encode Marco's conventions, confirmed by a 69-question style interview against 40 merged PRs and five personal repositories. Project conventions win where they conflict; read the neighbouring files first.
Mechanical rules (formatting, import order, enums, any, naming casing) are config, not guidance.
They live in eslint-recommendations.md and stay out of the rule files
on purpose.
React (frontend files only)
Effect, dependency, and ref discipline is separate from component structure:
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.
- 6d ago Changed · +2 lines · +96 tokens per session dd28784dad75
- 9d ago Changed · +54 lines · +1,417 tokens per session d403111eae53
- 1mo ago Changed · +3 lines · +112 tokens per session bf800228b982
- 2mo ago First seen · 98 lines · 1,354 tokens per session scan A cabddd321eea
ai-essentials AGENTS.md is an instructions file published in the GitHub repository tonyghiani/ai-essentials (7 stars, last pushed 4d ago), licensed MIT. It adds 2,979 tokens to every session, about $0.0119 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.
ai-essentials AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-essentials AGENTS.mdtonyghiani/ai-essentials | Instructions file | 7 | 4d ago | MIT | A | 2,979 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |