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/refactoringgit 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 | $0.01335 | $0.01335 |
| Opus 5 | $0.00668 | $0.00668 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
UKHO.GitHubCopilot.ToolKit refactoring.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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring guidance
Overview
These instructions define how refactoring work should be performed in this repository. The goal is to improve readability, maintainability, testability, and structure without changing intended behavior unless the work item explicitly calls for a functional change.
Scope
Applies to: src/**/*.cs, src/**/*.razor, src/**/*.razor.cs, test/**/*.cs
- Applies when restructuring existing production or test code under
src/andtest/. - These rules are additive to
/.github/copilot-instructions.md,/.github/instructions/csharp.instructions.md,/.github/instructions/tests.instructions.md, and any feature-specific instruction files. - For Blazor code, apply these rules to component markup, code-behind, and related view-model logic together.
Instructions
MUST
- Preserve observable behavior unless the request explicitly includes a behavior change.
- Treat routes, request and response shapes, rendered UI outcomes, validation rules, configuration keys, dependency injection registrations, service lifetimes, and persistence contracts as observable behavior.
- Apply established design principles when refactoring.
- Use Separation of Concerns to keep UI, application, domain, infrastructure, and test responsibilities distinct.
- Use the Single Responsibility Principle to ensure a type, component, or method has one clear reason to change.
- Use Dependency Inversion and Explicit Dependencies to depend on abstractions and constructor-injected collaborators instead of hidden ambient state or concrete infrastructure details.
- Use DRY to remove true duplication by centralizing shared behavior in one authoritative implementation.
- Prefer compiler-assisted or IDE-assisted refactorings for structural changes.
- Use safe rename for symbols instead of manual search-and-replace.
- Use extract method, extract local function, extract interface, move type to matching file, sync namespace and folder name, and move declaration near reference when those operations match the intended change.
- Review rename and move previews before applying changes when the refactoring spans multiple files, projects, or public-facing symbols.
- Keep each refactoring step small enough that build failures and regressions can be localized to a narrow change.
- Add or update automated tests when a refactor touches behavior-critical logic or when existing coverage is missing for the refactored path.
- Regression-focused tests MUST verify behavior, not implementation details.
- Preserve public contracts unless the request explicitly authorizes changing them.
- Preserve nullable annotations, asynchronous behavior, cancellation flow, and exception semantics unless the request explicitly authorizes changing them.
- When extracting shared logic, introduce the narrowest abstraction that removes current duplication or clarifies an existing responsibility.
- When moving or splitting C# types, keep one top-level type per file and ensure the file name, type name, folder, and namespace remain aligned.
- Introduce seams for testability through explicit dependencies and dependency injection rather than through hidden ambient state, service location, or direct instantiation of infrastructure-heavy collaborators.
- Validate the result after refactoring by running a build and the relevant automated tests for the affected area.
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 · 89 lines · 1,335 tokens per session scan A 0f377a2f3757
UKHO.GitHubCopilot.ToolKit refactoring.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 1,335 tokens to every session, about $0.0067 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.