Borrowing it
Nothing to install: this file belongs to stefaniuk/loadout. 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/stefaniuk/loadout/main/.github/instructions/readme.instructions.mdgit clone --depth 1 https://github.com/stefaniuk/loadoutWrote 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/stefaniuk/loadout/readme)<a href="https://agentmods.dev/instructions/stefaniuk/loadout/readme"><img src="https://agentmods.dev/badge/instructions/stefaniuk/loadout/readme/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/stefaniuk/loadout/readme"><img src="https://agentmods.dev/badge/instructions/stefaniuk/loadout/readme.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 | $0.03051 | $0.03051 |
| Opus 5.5 | $0.01220 | $0.01220 |
| Sonnet 5.5 | $0.00610 | $0.00610 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
loadout readme.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 1mo 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README Engineering Instructions 📘
These instructions define the required structure and content for every repository's top-level README so that users and engineers can trust it as the single onboarding entry point.
They must remain applicable to:
- Product and platform services (internal or open-source)
- Libraries, SDKs, tooling, and infrastructure repos
- Template or example projects that seed new services
They are non-negotiable unless an explicit ADR grants a scoped, time-bound exception.
Identifier scheme. Every normative rule carries a unique tag in the form [RD-<prefix>-NNN], where the prefix maps to the containing section (for example QR for Quick Reference, STR for Structure, SEC for Section requirements). Use these identifiers when planning or validating documentation work.
0. Quick reference (apply first) 🧠
- [RD-QR-001] Follow the canonical section order defined in [RD-STR-001] so readers always know where to find information.
- [RD-QR-002] Base every statement on evidenced sources per [RD-GOV-002]; never invent behaviour or guarantees.
- [RD-QR-003] Use explicit
TODO:placeholders whenever information is missing or unverified ([RD-GOV-003]). - [RD-QR-004] Keep the opening section short enough for readers to understand purpose, benefit, problem, and approach within 30 seconds ([RD-GOV-005], [RD-VAL-001]).
- [RD-QR-005] Quick start content must document prerequisites, setup, first run, and expected success indicators using repository-supported commands ([RD-SEC-007]–[RD-SEC-012]).
- [RD-QR-006] Always provide a Contributing path with links, dev setup, and quality commands ([RD-SEC-025]–[RD-SEC-028]).
- [RD-QR-007] Use relative links for all in-repo references and include the standard docs/security links when they exist ([RD-LNK-001]–[RD-LNK-002]).
- [RD-QR-008] Run the validation checklist in [RD-VAL-001]–[RD-VAL-006] before finalising any README change.
1. Purpose and outcomes 🎯
- [RD-PUR-001] The README must explain the project quickly and clearly to new readers.
- [RD-PUR-002] It must state why the reader should care by emphasising tangible benefits or outcomes.
- [RD-PUR-003] It must describe the problem the project solves and outline the high-level approach.
- [RD-PUR-004] It must provide a fast, reliable path to using the project successfully.
- [RD-PUR-005] It must provide a clear path for engineers to contribute, test, and extend the project.
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.
- 1mo ago Changed · +1 lines · +49 tokens per session 2f2d54116435
- 1mo ago First seen · 172 lines · 3,002 tokens per session scan A 35df5e1c0cff
loadout readme.instructions.md is an instructions file published in the GitHub repository stefaniuk/loadout (1 stars, last pushed yesterday), licensed MIT. It adds 3,051 tokens to every session, about $0.0122 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.