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/agents-mdgit 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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
UKHO.GitHubCopilot.ToolKit 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 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent operating guidance
This file defines the repository-level operating model for agents and contributors who create or maintain the reusable Copilot assets in this toolkit.
Purpose
Use this guidance to keep agentic work focused, efficient, and reviewable while preserving the repository's existing quality, wiki-first, and reusable-Microsoft-project expectations.
Core operating rules
- Prefer one primary outcome per chat, prompt, or agent execution. If the task changes materially, start a fresh thread or explicitly re-scope the work.
- Plan before acting on any non-trivial task. Do not iterate blindly through repeated trial-and-error.
- Keep responses lean by default. Avoid unnecessary narration, repeated summaries, or oversized intermediate output.
- Prefer scripts or reusable automation for repeatable inventory, validation, or transformation work.
- Cap tool output deliberately by using targeted file reads, narrow searches, and structured output where possible.
- Use precise evidence when referring to implementation details, preferably with
file:linereferences when the medium supports them. - Prefer semantic or code-graph search before repeated text grep when that gives a better signal-to-noise ratio.
- Choose model capability intentionally. Use lower-cost models for routine work when validated, and reserve the highest-judgment validated model (currently
gpt-5.4) for higher-judgment tasks. - Read stable context before volatile context so repeated work benefits from consistent grounding.
- Parallelize independent read-only investigation where it improves throughput without reducing clarity.
- Delegate broad research to subagents when available, then consume and preserve only the useful summary.
- Record stable operating guidance here and stable repository learnings in
lessons.mdwhen they are worth reusing. - Stop after three failed attempts at the same approach and surface the blocker, evidence, and recommended next move.
- Prefer targeted diff-based edits over full-file rewrites unless the task genuinely requires replacement.
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 · 40 lines · 555 tokens per session scan A 0005ee004de2
UKHO.GitHubCopilot.ToolKit AGENTS.md is an instructions file published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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.