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.
npx agentmods add instructions/ukho/ukho.githubcopilot.toolkit/goodgit clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKitWhat 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 | $0.01805 | $0.01805 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
UKHO.GitHubCopilot.ToolKit good.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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Good solution characteristics
Overview
These instructions describe what a good technical solution to a business problem should look like and move toward over time. In this file, solution means the whole technical response being delivered, from a small application or automation through to a distributed application. It does not mean a Microsoft or Visual Studio solution, nor does it mean an individual project file.
These instructions are for contributors creating or changing code, tests, infrastructure, documentation, prompts, agents, templates, or planning assets in repositories that support those technical solutions.
A good solution may not satisfy every characteristic immediately. Contributors should still consider these characteristics during each change, make proportionate improvements where practical, and document justified tradeoffs when constraints prevent full alignment.
A good solution should normally be cloneable and runnable by a new contributor with no local configuration or only a small, documented setup step. The solution should contain the resources needed to run the application locally, with suitable mocks, fakes, seeded data, or local containers for external systems where necessary. It should also let contributors run most, and ideally all, automated tests on a desktop with little effort.
It should run on current, supported platform versions where practical, such as supported .NET, C#, SQL Server, database drivers, JavaScript runtimes, operating systems, and cloud SDKs.
It should follow a cloud-first approach and strongly consider containers when they improve portability, deployment consistency, local development, or operational reliability.
It should be strongly cohesive and loosely coupled so responsibilities are clear, dependencies are intentional, and change remains localized.
Scope
Applies to: **/*
- Applies when creating or changing the technical solution structure, implementation, tests, infrastructure, documentation, repository guidance, or delivery workflow assets.
- Complements more specific scoped instruction files; when instructions conflict, prefer the more specific file for the affected language, framework, folder, or workflow.
- Treats these rules as solution-quality direction rather than a claim that every prompt or task can fully achieve every characteristic in one change.
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.
- yesterday First seen · 121 lines · 1,805 tokens per session scan A b7438a470fd3
UKHO.GitHubCopilot.ToolKit good.instructions.md is an instructions file published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,805 tokens to every session, about $0.0090 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.