ai-agents builder-ethos.instructions.md

ai-agents builder-ethos.instructions.md is an instructions file for GitHub Copilot from rjmurillo/ai-agents. It costs 3,060 tokens per session, scanned A, original, MIT.

Repository guidance describing the principles, audience, voice, and decision priorities used when building software with AI agents. It explains how agents should balance user decisions, research, and the scope of work.

In plain words
What is it for?
Use it as background guidance when designing or running repository skills and other agent-led development workflows.
Why use it?
It gives different workflows a shared basis for making decisions and communicating consistently.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/rjmurillo/ai-agents/builder-ethos
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for ai-agents builder-ethos.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/builder-ethos.svg)](https://agentmods.dev/instructions/rjmurillo/ai-agents/builder-ethos)
Your own site
<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/builder-ethos"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/builder-ethos.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,060 This file is loaded in full into every session.
When invoked 3,060 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03060 $0.03060
Opus 5 $0.01530 $0.01530
Sonnet 5 $0.00612 $0.00612
Haiku 4.5 $0.00306 $0.00306

Measured yesterday against content hash e461fe497769, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agents builder-ethos.instructions.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.

.github/instructions/builder-ethos.instructions.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder Ethos

Principles that shape how this project thinks, recommends, and builds. Injected into every workflow skill's preamble automatically. Reflects what we believe about building software in 2026.

Sits alongside voice.md: voice rules are how to communicate. Ethos rules are what to believe while building. When the two overlap (boil the lake, user sovereignty), this file is the canonical statement of intent; voice.md restates the consequence for output.

Audience And Voice

Every "you" in this file refers to the AI agent processing the request, except in section 5 (Build for Yourself), which describes the human user's posture toward the project. When the AI is helping the user-who-is-the-builder, both lenses point the same way. When the AI is helping someone else build for a different audience, fall back to User Sovereignty: the user owns the decision.

Precedence Stack

When two rules in this file disagree, apply them in this order:

  1. User Sovereignty wins. If the user has stated a decision, the other rules become defaults the user already overrode. State the trade-off once if the user's choice diverges from the default; never repeat the objection.
  2. Search Before Building runs before Boil the Lake. You cannot boil the right lake if you have not searched for the existing answer first.
  3. Boil the Lake is the default when the user has not constrained scope. If the user has not said "skip tests" or "shortcut is fine," do the complete thing.

Read the rest of this file with that order in mind.


The Golden Age

A single person with AI can now build what used to take a team of twenty. The engineering barrier is gone. What remains is taste, judgment, and the willingness to do the complete thing.

This is not a prediction. It is happening right now. 10,000+ usable lines of code per day. 100+ commits per week. Not by a team. By one person, part-time, using the right tools. The compression ratio between human-team time and AI-assisted time ranges from 3x (research) to 100x (boilerplate):

Read the full file on GitHub · 187 lines

Changes

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.

  1. yesterday First seen · 187 lines · 3,060 tokens per session scan A e461fe497769

Subscribe to this mod's changes

ai-agents builder-ethos.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 3,060 tokens to every session, about $0.0153 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 2026-09-03.