Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/AGENTS.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/agents-md)<a href="https://agentmods.dev/instructions/rajbos/ai-engineering-fluency/agents-md"><img src="https://agentmods.dev/badge/instructions/rajbos/ai-engineering-fluency/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/rajbos/ai-engineering-fluency/agents-md"><img src="https://agentmods.dev/badge/instructions/rajbos/ai-engineering-fluency/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 | $0.06461 | $0.06461 |
| Opus 5.5 | $0.02584 | $0.02584 |
| Sonnet 5.5 | $0.01292 | $0.01292 |
| Haiku 4.5 | $0.00646 | $0.00646 |
Grade A, and why
ai-engineering-fluency 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 yesterday.
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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineering Fluency — Repository Instructions
(Previously known as the "GitHub Copilot Token Tracker")
This document provides top-level guidance for AI agents contributing to this repository. Detailed, folder-specific instructions live in .github/instructions/ and are applied automatically by Copilot when you work inside those folders.
Repository Structure
Run ls -a (or git ls-files | cut -d/ -f1 | sort -u) for the live top level.
/
├── AGENTS.md ← This file (the canonical content)
├── CLAUDE.md ← Claude Code entry point (imports this file and sharing-server/AGENTS.md)
├── build.ps1 / dev.ps1 ← Root build orchestrator / local dev helper
├── src/ ← Shared TypeScript sources + JSON data files
│ (session parsing, token estimation, adapters —
│ consumed by vscode-extension/ and cli/)
├── vscode-extension/ ← VS Code extension (TypeScript / Node.js)
├── cli/ ← Command-line tool (TypeScript / Node.js)
├── copilot-app/ ← GitHub Copilot app canvas, shipped as the `ai-fluency-canvas`
│ Copilot plugin (plain Node .mjs, no build; runs the CLI)
├── visualstudio-extension/ ← Visual Studio extension (C# / .NET)
├── jetbrains-plugin/ ← JetBrains IDE plugin (Kotlin / Gradle / IntelliJ Platform)
├── desktop/ ← Electron tray app; reuses vscode-extension's built
│ webview bundles and cli/vscode-extension stats logic
├── badge-app/ ← MicroPython app for the GitHub Universe 2026 badge, showing
│ the fluency.json the extension writes (plus preview/QR tools)
├── sharing-server/ ← Self-hosted API server + web dashboard for sharing
│ fluency data across a team (TypeScript, SQLite, Docker)
├── release-video/ ← Local release-video generator: the What's New
│ catalog + the visual-view-diff harness ->
│ narrated MP4 (TypeScript, FFmpeg, local TTS)
├── scripts/ ← Build/release/CI helper scripts (Node, PowerShell, Python)
├── omp-segment/ ← Oh My Posh terminal prompt segment showing token usage
├── assets/ ← Logos and other static brand assets
├── docs/ ← Shared documentation
├── screenshots/ ← Only a `.vscode/settings.json` pointing the sample-data
│ setting at sample session data. `scripts/capture-screenshots.ps1`
│ (manual, Windows-only, run by `scripts/pre-release.js`) names it
│ but does not currently open it; agents must not run that script
├── .vscode/ ← Shared VS Code settings, tasks and launch configs
│ (for human developers; see "Never Launch a Real Editor/IDE Instance")
├── .devcontainer/ ← Dev container definition (see "DevContainer Terminal Behavior")
├── .claude/ ← Claude Code subagents (`agents/`) and skills (`skills/`),
│ mirrored from `.github/` (see the mirroring section)
├── .github/
│ ├── copilot-instructions.md ← Pointer to this file (`See ../AGENTS.md`)
│ ├── agents/ , skills/ ← Copilot custom agents and Agent Skills (mirrored to `.claude/`)
│ ├── workflows/ ← CI/CD
│ ├── plugin/marketplace.json ← Copilot plugin marketplace catalog (lists copilot-app/)
│ └── instructions/ ← Folder-specific guides (see the table below)
└── README.md, CONTRIBUTING.md, CHANGELOG.md, SECURITY.md, SUPPORT.md, LICENSE, and the generated
LOC_STATS.md (other generated reports, such as the hardcoded-strings report, are git-ignored)
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.
- yesterday First seen · 309 lines · 6,461 tokens per session scan A e5c537286319
ai-engineering-fluency AGENTS.md is an instructions file published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 6,461 tokens to every session, about $0.0258 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 2026-10-26.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.