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/work-packagesgit 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 | $0.01292 | $0.01292 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
UKHO.GitHubCopilot.ToolKit work-packages.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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work package documentation instructions
Overview
These instructions define how to document each incremental unit of work so it can be delivered iteratively and reviewed consistently. They are for contributors creating or updating work items under ./docs/.
Scope
These rules apply when adding or updating documentation for a unit of work. They are primarily concerned with content under ./docs/00x-work/.
Instructions
MUST
-
You MUST maintain a project-level business requirements document at
./docs/business-requirements.md.- This document defines the business context, desired outcomes, and high-level requirements for the overall initiative.
- It is the foundation upon which systems analysis and work packages are defined.
-
You MUST NOT draft a new
./docs/00x-work/work package unless the user or task explicitly requests one. -
You MUST maintain a project-level systems analysis document at
./docs/systems-analysis.mdbefore commencing any work packages.- This document refines the business requirements into system boundary/context, use cases, business rules, analysis-level requirements, and quality attributes.
- It must remain implementation-agnostic and must not replace per-work-package requirements/specification/plan documents.
-
You MUST review the relevant
./docs/wiki/pages before creating or updating work-package requirements, technical specifications, plans, review reports, or execution status so the work stays grounded in the current project understanding. -
You MUST create a dedicated folder under
./docs/for each unit of work, named00x-workwhere00xis a zero-padded sequence number (e.g.001) andworkis a brief description of the task (for example:001-add-order-endpoint). -
You MUST include a
requirements.mdin each./docs/00x-work/folder. -
You MUST ensure each work package
requirements.mdaligns with and links to../business-requirements.md. -
You MUST produce a technical specification from the requirements and store it as
technical-specification.mdin the same./docs/00x-work/folder. -
You MUST create a
plans/subfolder inside each./docs/00x-work/folder when that work package needs one or more plans. -
You MUST create the initial delivery plan based on both the requirements and technical specification and store it as
plans/001-delivery-plan.mdin the same work-package folder. -
You MUST store any additional work-package plan documents in that same
plans/subfolder and name them with the next zero-padded sequence prefix (for exampleplans/002-some-refactor-plan.md). -
Work package
requirements.mddocuments MUST remain implementation-agnostic.- Refer to a data store for configuration rather than naming SQL Server directly in requirements-level documents.
-
You MUST keep the
00xnumber monotonically increasing (do not reuse a prior number for a different work item). -
You MUST keep each work item's documentation self-contained within its
./docs/00x-work/folder and itsplans/subfolder. -
You MUST update the relevant documentation under
./docs/wiki/before marking any numbered plan complete when the implemented behavior, architecture, API surface, runtime behavior, operator workflow, local development guidance, or testing approach has changed. -
When asked to review a work package, you MUST create the review report as a physical markdown file within that work package, not only as chat output.
-
When creating a delivery plan from refactoring advice, you MUST scope the plan to that refactor objective rather than to existing work-package docs unless explicitly instructed to reuse them.
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 · 73 lines · 1,292 tokens per session scan A 455ea33e8409
UKHO.GitHubCopilot.ToolKit work-packages.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 1,292 tokens to every session, about $0.0065 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.