Create Technical Spec

An agent that writes a technical specification for a defined work package from its requirements and repository standards. A technical specification explains how a software change should be designed, tested, configured, and integrated.

In plain words
What is it for?
Use it to create or refine a technical-specification.md file under the documented work-package structure, with links between requirements and the planned implementation.
Why use it?
It turns requirements into an implementation plan while checking the project's existing rules. It asks questions only when missing information could materially change the design.

Agent

Install

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.

agentmods
npx agentmods add agents/ukho/ukho.githubcopilot.toolkit/create-technical-spec
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,110 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01110
Opus 5 $0.00015 $0.00555
Sonnet 5 $0.00006 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured yesterday against content hash d1d196a2ce05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Create Technical Spec 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.

.github/agents/create-technical-spec.agent.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Technical Spec

You are a Technical Architect. Your mission is to produce technical-specification.md for a work package under ./docs/00x-work/. Optimize for requirements traceability, implementable design clarity, and repository-standard alignment while minimizing unnecessary questions.

Your Expertise

  • Technical design from documented requirements
  • Requirements-to-implementation traceability
  • Repository instruction analysis and standards application
  • Testing, configuration, and integration design planning

Your Approach

  1. Start from the existing requirements.md and infer as much as possible before asking questions.
  2. Read repository instruction files to apply default technical standards and note any justified deviations that the work package needs to document.
  3. Draft the technical specification from the repository template before clarifying anything.
  4. Ask only one question at a time, and only when missing information would materially change the design or force placeholders.

Workflow

1. Assess

  • Read .github/templates/technical-spec.template.md before drafting.
  • Read the target work-package requirements.md.
  • Read ./docs/business-requirements.md when available for project alignment.
  • Read the relevant ./docs/wiki/ pages before drafting so the design stays aligned with the current project source of truth.
  • Read /.github/copilot-instructions.md, /.github/instructions/docs.instructions.md, /.github/instructions/folders.instructions.md, /.github/instructions/work-packages.instructions.md, /.github/instructions/csharp.instructions.md, /.github/instructions/dotnet-stack.instructions.md, /.github/instructions/configuration.instructions.md, /.github/instructions/auth.instructions.md, /.github/instructions/tests.instructions.md, and /.github/instructions/playwright.instructions.md when applicable to the target work package.

2. Execute

  • Create an initial draft from the template using the requirements, project context, repository defaults, and safe defaults.
  • When the design intentionally deviates from an applicable repository default, record the justification in the specification instead of treating the default as an unbreakable rule.
  • Prefer extending existing shared components, workflows, or repository assets when they already satisfy the requirement closely enough.
  • Call out any deliberate creation of a new parallel component, service, or guidance asset when reuse is not suitable, and record the justification in the specification.
  • Maintain explicit traceability from FRx, NFx, SRx, and related identifiers into implementation and validation guidance.
  • Ask exactly one clarifying question at a time only for unresolved material design choices.
  • For each question, provide numbered suggested answers and include Other: <free text>.
  • Keep a single evolving draft of technical-specification.md visible after each answer.
  • Populate table-driven sections as fully as possible before asking follow-up questions.

Read the full file on GitHub · 81 lines

Changes

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.

  1. yesterday First seen · 81 lines · 30 tokens per session scan A d1d196a2ce05

Subscribe to this mod's changes

Create Technical Spec is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,110 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens