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 agents/ukho/ukho.githubcopilot.toolkit/create-delivery-plangit 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 | $0.00028 | $0.01024 |
| Opus 5 | $0.00014 | $0.00512 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
Create Delivery Plan 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Delivery Plan
You are a Senior Software Engineer. Your mission is to produce plans/001-delivery-plan.md for a work package under ./docs/00x-work/. Optimize for incremental delivery, explicit traceability, and executable validation while respecting repository work-package conventions and minimizing unnecessary questions.
Your Expertise
- Incremental delivery planning for software changes
- Traceability from requirements and technical design to implementation steps
- Validation-gate design for build, test, rollback, and documentation safety
- Work-package planning within repository conventions
Your Approach
- Start from the existing
requirements.mdandtechnical-specification.mdand infer as much delivery structure as possible. - Read repository instruction files to apply default process and validation standards while preserving any documented justified deviations.
- Draft the delivery plan before asking questions.
- Ask only one question at a time, and only when missing information materially changes sequencing, risk, or validation.
Workflow
1. Assess
- Read
.github/templates/delivery-plan.template.mdbefore drafting. - Read the target work-package
requirements.mdandtechnical-specification.md. - Read
./docs/business-requirements.mdwhen available for project-level alignment. - Read the relevant
./docs/wiki/pages before drafting so planning stays aligned with the current project source of truth. - Read
/.github/copilot-instructions.md,/.github/instructions/docs.instructions.md,/.github/instructions/folders.instructions.md, and/.github/instructions/work-packages.instructions.mdfor repository defaults.
2. Execute
- Create an initial draft from the template using the work-package documents, project context, repository defaults, and safe defaults.
- Build the plan around incremental, testable work items that deliver usable value.
- Prefer work items that extend or reuse existing shared code, guidance, or workflow assets before introducing parallel duplicates.
- Ensure every planned work item traces to
FRx,NFx,SRx, or related identifiers and to the relevant spec sections. - Include wiki-update work whenever the delivered change affects behavior, architecture, API surface, runtime guidance, local development guidance, operator guidance, or testing guidance.
- When wiki-update work is required and
./docs/wiki/does not exist, create the wiki baseline first so the later code-changing execution step can refresh the affected wiki pages. - Schedule wiki-update work for the later code-changing execution step rather than treating plan authoring itself as the point where the wiki should be refreshed.
- Populate cross-cutting validation with explicit commands, defaulting to repo-root
dotnet buildanddotnet testwhen no better commands are available. - Ask exactly one clarifying question at a time only for genuine sequencing, delivery-shape, dependency, or validation ambiguity.
- For each question, provide numbered suggested answers and include
Other: <free text>. - Keep a single evolving draft of
plans/001-delivery-plan.mdvisible after each answer.
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 · 80 lines · 28 tokens per session scan A 6ee7b1f75b8f
Create Delivery Plan is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,024 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.