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/aiappsgbb/awesome-gbb/agents-mdgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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/aiappsgbb/awesome-gbb/agents-md)<a href="https://agentmods.dev/instructions/aiappsgbb/awesome-gbb/agents-md"><img src="https://agentmods.dev/badge/instructions/aiappsgbb/awesome-gbb/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 | $0.40065 | $0.40065 |
| Opus 5 | $0.20033 | $0.20033 |
| Sonnet 5 | $0.08013 | $0.08013 |
| Haiku 4.5 | $0.04007 | $0.04007 |
Grade C, and why
awesome-gbb AGENTS.md scanned grade C with 2 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://aka.ms/install-azd-script-linux | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://aka.ms/install-azd-script-linux | bash How it starts
The opening of the file, as written. The whole thing — 3,075 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Contributor & Sub-Agent Guide
Rules for anyone (human or AI) who edits this repo. Read this before opening a PR, asking a sub-agent to refactor a skill, or running a mass scrub / sync pass. Violating an invariant here breaks downstream consumers in subtle ways that won't fail CI.
This repo is the canonical home of the awesome-gbb skill catalog. The
README covers what each skill does. This file covers how to
safely change them.
1 · Repo layout (what lives where)
awesome-gbb/
├── README.md # Public catalog (skills index, install instructions)
├── AGENTS.md # ← you are here
├── plugin.json # Single plugin manifest ("skills": "skills/")
├── skills/ # SOURCE OF TRUTH for every skill
│ └── <skill-name>/
│ ├── SKILL.md # Skill definition (frontmatter + instructions)
│ ├── README.md # Optional extended docs
│ ├── references/ # Optional: scaffolds, templates, canon data
│ │ └── … # SemVer-stable; consumed by the SKILL at runtime
│ └── templates/ # Optional: copy-paste templates (Bicep, Dockerfile, …)
└── .github/plugin/
└── marketplace.json # Lists the plugin for `copilot plugin marketplace add`
There is no monorepo build step for individual skills — each
skills/<name>/SKILL.md is a self-contained markdown contract loaded
directly by the runtime (Copilot CLI, Copilot Desktop App, VS Code agent
mode, Claude Code, etc.).
The repo IS the plugin — plugin.json at the repo root declares
"skills": "skills/", so the CLI auto-discovers all skills. No copies,
no sync step, no plugins/ directory.
2 · Core invariants (do not break these)
These rules govern every edit, however small. If you can't satisfy all of them, do not commit — open a discussion first.
2.1 Skills are agnostic
A skill is a reusable building block. It must read sensibly to a stranger who has never seen the PoC, customer, or repo it was last used in.
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.
- today Changed · +5 lines · +54 tokens per session ffd695374fdc
- 5d ago First seen · 3,070 lines · 40,011 tokens per session scan C d6aac80895ca
awesome-gbb AGENTS.md is an instructions file published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed yesterday), licensed MIT. It adds 40,065 tokens to every session, about $0.2003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).