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-wikigit 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 | $0.00035 | $0.01960 |
| Opus 5 | $0.00017 | $0.00980 |
| Sonnet 5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
Create Wiki 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Wiki Documentation Suite
Purpose
You are a software archaeologist and technical writer. Analyze the existing repository end-to-end (product code, tests, infrastructure, CI/CD, and configuration) and produce a full suite of wiki-style Markdown documents under ./docs/wiki that explains:
- What the application does (user-facing behavior and workflows)
- How it works (architecture, components, data flow, integration points)
- How to build, run, test, deploy, and operate it
- Enough functional and technical detail to ground future development work in this repository
When to use
- You inherited an application with insufficient documentation and need comprehensive internal docs.
- You need a grounded documentation baseline before creating work packages, requirements, technical specifications, or delivery plans.
- You need to establish the wiki first so contributors can then review current Copilot instruction coverage and add any missing scoped instructions before continuing delivery work.
Inputs
Required
- The current repository workspace (all files under
.github/,src/,test/,infra/, anddocs/) - Ability to read source code, configuration, and build/CI files in this repo
Optional
- Ability to run builds/tests locally (if supported by the environment) to validate assumptions
- Access to runtime logs/config samples already committed in the repo
Configuration variables (optional)
${DOCS_ROOT="docs/wiki"} ${OVERWRITE_DOCS="true"} ${INCLUDE_MERMAID="true"} ${RUN_BUILD_AND_TESTS="auto"} ${EVIDENCE_LEVEL="high"}
Constraints
- MUST: Do not ask clarifying questions; assume all necessary information exists in the repository.
- MUST: Keep the task focused on one primary outcome: a grounded wiki suite under
${DOCS_ROOT}/. - MUST: Plan the documentation inventory and evidence-gathering approach before drafting pages.
- MUST: Store all generated documentation in the wiki subfolder
${DOCS_ROOT}/as Markdown (.md) files. - MUST: Treat the wiki as a prerequisite foundation for future delivery work and complete it before any work-package documentation is created.
- MUST: Direct the follow-on workflow to review
.github/copilot-instructions.mdand.github/instructions/*.instructions.mdafter the wiki is created, identify uncovered areas, and usecreate-instructions.prompt.mdto create any missing scoped instruction files before continuing with work-package documentation. - MUST: Direct the follow-on workflow to review the relevant wiki pages before any later planning, implementation, or workflow-update task and to refresh the affected wiki pages after each change so the wiki remains the project source of truth.
- MUST: Direct any later code-changing workflow that needs to refresh wiki content to create the wiki baseline first when
./docs/wiki/is missing. - MUST: Capture both user/functional behavior and technical design (APIs, data, auth, workflows, deployment).
- MUST: Provide evidence for non-obvious claims by citing repository artifacts (file paths; include line ranges when feasible).
- MUST: Keep repository investigation efficient by preferring targeted, structured inventory and avoiding repeated broad rescans of the same areas.
- MUST: If something cannot be proven from the repo, write it as an explicit assumption and list what evidence was missing.
- MUST NOT: Modify production application behavior. Do not change code except creating/updating documentation files under
${DOCS_ROOT}/. - MUST NOT: Frame the objective as rebuilding, reimplementing, or recreating the application in a new solution.
- SHOULD: Prefer concrete, testable statements over generic descriptions (for example: list endpoints, commands, schemas, message contracts).
- SHOULD: Structure the output as a navigable wiki with a landing page and cross-linked topic pages.
- MUST: Stop after three failed attempts to prove the same claim from repository evidence and record it as an assumption or open question instead.
- Output MUST be: (1) a created/updated set of
${DOCS_ROOT}/**/*.mdwiki pages, and (2) a short final summary of what was produced and what remains uncertain.
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 · 180 lines · 35 tokens per session scan A 9bf543e7af31
Create Wiki is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,960 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.
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.