Borrowing it
Nothing to install: this file belongs to user-w-ui/search-before-build. 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/user-w-ui/search-before-build/main/AGENTS.mdgit clone --depth 1 https://github.com/user-w-ui/search-before-buildWrote 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/user-w-ui/search-before-build/agents-md)<a href="https://agentmods.dev/instructions/user-w-ui/search-before-build/agents-md"><img src="https://agentmods.dev/badge/instructions/user-w-ui/search-before-build/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/user-w-ui/search-before-build/agents-md"><img src="https://agentmods.dev/badge/instructions/user-w-ui/search-before-build/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00857 | $0.00857 |
| Opus 5.5 | $0.00343 | $0.00343 |
| Sonnet 5.5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
search-before-build 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 20d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a multi-host skill package, not a compiled application. .claude-plugin/plugin.json (Claude Code), .codex-plugin/plugin.json (Codex, installed by bin/install.mjs), index.js (OpenCode, skill ids search-before-build-<skill>), the pi key in package.json, and the root plugin.json (Agent Plugins) expose the shared workflows in skills/: assess evaluates an idea or an existing project from whatever material the user supplies, and quick-search gives a fast, preliminary look at what already exists. Their internal candidate-research workflow lives in references/research-method.md; source-specific rules live in the other files under references/. The one-time installer is scripts/setup-github-mcp.mjs; the temporary result viewer is rendered by scripts/render-report.mjs from assets/report-viewer.html. Keep shared skill instructions platform-neutral; naming host-specific tools is fine only as non-exhaustive examples of a capability. tests/validate_plugin.py checks structure and behavioral invariants. Persisted reports are optional and belong in docs/search-before-build/<topic-slug>/<competitor-slug>.md only after an explicit user request.
Build, Test, and Development Commands
The decision kernel in src/ builds to dist/ with npm run build:kernel; commit the rebuilt dist/ with kernel changes. Run these commands from the repository root:
claude plugin validate --strict .
python tests/validate_plugin.py
npm test
claude --plugin-dir /path/to/search-before-build
The first command validates the Claude manifest and skill metadata. The second checks the manifests, skill boundaries, reference files, report structure, and showcase. The third runs the kernel and host tests. The fourth loads the Claude package for an interactive smoke test. Invoke /search-before-build:assess <idea or path> or /search-before-build:quick-search <idea> after loading it. Validate the Codex manifest with Codex's plugin validator before publishing a Codex marketplace entry.
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.
- 20d ago Changed · +2 tokens per session 8f9b327bab8f
- 26d ago Changed · +1 lines · +186 tokens per session 8ebecc45aba7
- 2mo ago First seen · 32 lines · 669 tokens per session scan A dbcf7e5effeb
search-before-build AGENTS.md is an instructions file published in the GitHub repository user-w-ui/search-before-build (133 stars, last pushed 20d ago), licensed MIT. It adds 857 tokens to every session, about $0.0034 per session on Opus 5.5. 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.
search-before-build AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| search-before-build AGENTS.mduser-w-ui/search-before-build | Instructions file | 133 | 20d ago | MIT | A | 857 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |