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/bbartling/niagara4-vibe-code-addict/agents-mdgit clone --depth 1 https://github.com/bbartling/niagara4-vibe-code-addictWrote 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/bbartling/niagara4-vibe-code-addict/agents-md)<a href="https://agentmods.dev/instructions/bbartling/niagara4-vibe-code-addict/agents-md"><img src="https://agentmods.dev/badge/instructions/bbartling/niagara4-vibe-code-addict/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 5.1 | $0.00464 | $0.00464 |
| Opus 5 | $0.00232 | $0.00232 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
niagara4-vibe-code-addict 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.
What it actually says
AGENTS.md — Niagara Vibe Coding (Completed Code Output)
1. 🎯 Core Mission & Agent Contract
1.1 Agent Task (Your Goal)
Given:
- the Niagara auto-generated
ProgramImplstructure, - the available slot getter/setter methods,
- and the user task description,
you must produce a paste-ready completed Program Source code block.
The returned code must be:
- complete
- copy/paste ready
- self-contained
- not chunked
- not pseudo-code
- not partial
The user works inside Niagara where imports, class, and slots already exist.
You MUST generate:
- stateful fields
- full onStart()
- full onExecute()
- full onStop()
- helper methods
- constants
1.2 Required Output Format
Return exactly ONE fenced Java block.
It must include:
- fields
- full method headers + bodies
- helpers
NO:
- TODOs
- placeholders
- chunked output
- explanations between code
2. ❗ Core Directives
2.1 Always Return Completed Code
Default behavior: 👉 FULL Program Source
Only return partial snippets if explicitly requested.
2.2 Respect Niagara Boundaries
DO NOT generate:
- imports
- class declaration
- getters/setters
DO generate:
- fields
- lifecycle methods
- helpers
2.3 Copy/Paste First Design
Optimize for:
- direct paste into Workbench
- compile-ready logic
- no assembly required
2.4 Vibe-Coder Rule
When unsure: 👉 choose FULL implementation over explanation
3. 📤 Final Output Spec
Return:
// full program source
Must include:
- fields
- onStart
- onExecute
- onStop
- helpers
4. 🚫 Forbidden Outputs
- chunked code
- method-only bodies (unless asked)
- pseudo-code
- explanations replacing code
- incomplete logic
5. ✅ Success Criteria
A user should be able to:
- Copy
- Paste into Niagara ProgramObject
- Run
WITHOUT modifying 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 First seen · 127 lines · 464 tokens per session scan A 27594146ff01
niagara4-vibe-code-addict AGENTS.md is an instructions file published in the GitHub repository bbartling/niagara4-vibe-code-addict (53 stars, last pushed yesterday), licensed MIT. It adds 464 tokens to every session, about $0.0023 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 2026-08-30.
Other instructions, from other repositories
open-fdd AGENTS.md
AGENTS.md instructions for bbartling/open-fdd, covering agent guide (container stack + external agents), start session, or: react (no fieldbus) / csv, rust hygiene (agents) and safe scripts.
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.
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.
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.