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/hardy4yooz/buzz-web/agents-mdgit clone --depth 1 https://github.com/hardy4yooz/buzz-webWrote 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/hardy4yooz/buzz-web/agents-md)<a href="https://agentmods.dev/instructions/hardy4yooz/buzz-web/agents-md"><img src="https://agentmods.dev/badge/instructions/hardy4yooz/buzz-web/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 | $0.01492 | $0.01492 |
| Opus 5 | $0.00746 | $0.00746 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
buzz-web 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file defines repository-wide rules for coding agents and automated contributors. Human
contributors should also read CONTRIBUTING.md. Instructions in a more deeply
nested AGENTS.md, if one is added later, take precedence for that subtree.
Project Boundary
Buzz Web is a browser client for an existing Buzz Relay. Keep these boundaries explicit:
web/is the React/Vite single-page application. It may use Relay WebSocket and HTTP protocols, browser storage, and browser-safe libraries.agent-control/is an optional, separately deployed Node service that maps authorized signed requests to exact systemd units.deploy/packages the Web client only. It must not create, migrate, or mutate Relay databases, buckets, Git storage, networks, or credentials.- The Relay, desktop/mobile clients, and agent runtimes are upstream or external systems. Do not copy server behavior into the browser to simulate a feature.
If a requested action has no implemented and authorized backend operation, hide it and record the gap in the Roadmap. Do not ship a control that only changes local presentation while implying a Relay write succeeded.
Repository Map
web/src/app/ router and application shell
web/src/features/ feature-owned UI, hooks, and domain logic
web/src/shared/api/ persistent Relay and media clients
web/src/shared/config/ public runtime configuration
web/src/shared/i18n/ all application-owned UI copy
web/src/shared/lib/ protocol and browser utilities
web/src/shared/ui/ reusable visual primitives
web/tests/e2e/ Playwright user journeys
agent-control/ optional signed agent-start service
deploy/ container and edge-routing examples
docs/ operator documentation
Keep code feature-local until at least two features need the same stable behavior. shared/ is not
a miscellaneous folder.
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 · 161 lines · 1,492 tokens per session scan A 2ec1ac63ceeb
buzz-web AGENTS.md is an instructions file published in the GitHub repository hardy4yooz/buzz-web (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,492 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
nostr-auth-agents AGENTS.md
AGENTS.md instructions for dyegolara/nostr-auth-agents, covering agents.md — nostr-auth for coding agents, what this tool does, when to run it, quick invocation and recommended flow.
nostr-mcp-server CLAUDE.md
Instructions for AustinKelsay/nostr-mcp-server, covering claude.md, project overview, common commands, run all tests and run a specific test file.
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.
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.
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.