Borrowing it
Nothing to install: this file belongs to cobusgreyling/grok-build-showcase. 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/cobusgreyling/grok-build-showcase/main/AGENTS.mdgit clone --depth 1 https://github.com/cobusgreyling/grok-build-showcaseWrote 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/cobusgreyling/grok-build-showcase/agents-md)<a href="https://agentmods.dev/instructions/cobusgreyling/grok-build-showcase/agents-md"><img src="https://agentmods.dev/badge/instructions/cobusgreyling/grok-build-showcase/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 | $0.01714 | $0.01714 |
| Opus 5 | $0.00857 | $0.00857 |
| Sonnet 5 | $0.00343 | $0.00343 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
grok-build-showcase 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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Grok Build Rules for grok-build-showcase
This file encodes project-specific instructions for Grok (and compatible agents). It is automatically discovered and appended to the system prompt when working in this repository (or any subdirectory).
Purpose: Make every Grok Build session in this repo maximally productive, safe, and consistent with the showcase's own best practices.
Coding Standards
- Language: TypeScript (strict mode). All new code must be
.ts. - Module system: ESM only (
"type": "module"in package.json). Useimport/export. - Style:
- Prefer
const, useletonly when reassignment is required. - Use functional patterns and pure functions in
core/. - Command handlers in
commands/should be thin (parse args → call core → report). - 100 character line length soft limit.
- Meaningful names. Avoid abbreviations except well-known ones (e.g.
cli,fs).
- Prefer
- Error handling: Validate at system boundaries (CLI input, file reads, external data). Fail fast with clear messages.
- No
any: Useunknown+ type guards or proper interfaces.
Build, Test & Verification
Mandatory before claiming work complete (on any non-trivial change):
npm run typechecknpm test- Manual smoke test of the affected command(s) (
npm run dev -- <command> ...)
For complex or risky work:
- Use the
checkskill (/checkor by following its verifier subagent pattern) or manually spawn a verification subagent. - Re-run the full test suite after fixes.
- A broken build or failing tests = automatic FAIL. Fix before proceeding.
Test guidelines:
- Place tests in
tests/. - Use real fixtures under
tests/fixtures/(good-project vs minimal-project) rather than heavy mocking. - Cover core logic (auditor, skill-parser, ignore handling) thoroughly.
- CLI integration can be lighter (focus on happy + error paths).
Git & Version Control
- Branch names:
feature/,fix/,chore/,docs/prefixes preferred. - Commit messages: conventional commits style (
feat:,fix:,docs:,chore:,refactor:). - Never commit directly to
main. Use branches + PRs for anything non-trivial. - Keep commits focused and atomic. Update tests/docs in the same commit when behavior changes.
- Run verification steps locally before pushing.
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.
- 8d ago First seen · 154 lines · 1,714 tokens per session scan A 03415e80661c
grok-build-showcase AGENTS.md is an instructions file published in the GitHub repository cobusgreyling/grok-build-showcase (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,714 tokens to every session, about $0.0086 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
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.