Borrowing it
Nothing to install: this file belongs to rjmurillo/ai-agents. 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/rjmurillo/ai-agents/main/.github/instructions/search-before-building.instructions.mdgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/search-before-building)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/search-before-building"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/search-before-building.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 | $0.01627 | $0.01627 |
| Opus 5 | $0.00813 | $0.00813 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
ai-agents search-before-building.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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Before Building
Before building anything unfamiliar, search first. Operational rule. Pairs with the sibling rule builder-ethos.md section 2, which explains the philosophy. This file says what to do.
Sibling reference, not link: this rule file is mirrored into multiple instruction trees under different file names (builder-ethos.md in .claude/rules/, builder-ethos.instructions.md in .github/instructions/ and src/copilot-cli/instructions/). A relative link breaks in two of the three trees. Look the file up by name in whichever tree the reader is in.
When To Apply
Trigger this rule when any of the following is true:
- The task uses a runtime feature, library, framework, or platform you have not touched in this codebase before.
- The task asks for a pattern (retry, idempotency key, circuit breaker, queue topology, schema migration) that has a known canonical shape.
- The task is in a domain you do not have a memory or ADR for.
- You are diagnosing a failure rather than building: a red check, a blocked push, a rejected API call. This repo's memory corpus covers CI, git, and PR-gate quirks densely, so the cause is often already written down. Re-deriving it is the expensive miss, and no gate catches it.
- You catch yourself starting from a blank file with no reference open.
When to skip the search. Skip when the edit only modifies code already open in the conversation context AND introduces no new APIs, libraries, or patterns. If either condition fails, run at least Layer 1. Search has a cost; do not search for the sake of searching, but do not skip because you "feel familiar" either. Familiarity without a recent read of the file is a hallucination signal.
The Three Layers
| Layer | Source | Action |
|---|---|---|
| 1. Tried and true | Standard patterns, runtime built-ins, this codebase's existing solutions | Do not reinvent. Find the existing shape and use it. |
| 2. New and popular | Blog posts, ecosystem trends, fresh libraries | Scrutinize. Crowd can be wrong. Inputs to thinking, not answers. |
| 3. First principles | Reasoning from the specific problem | Prize above the other two. Where the leverage lives. |
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 · 89 lines · 1,627 tokens per session scan A 766f6133fa27
ai-agents search-before-building.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 1,627 tokens to every session, about $0.0081 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.
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).
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).
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.
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.