What is OpenUKPublicDataMCP AGENTS.md?

Repository instructions for coordinating multiple coding agents on a shared project.

Use them to claim work, lock files, update project records through scripts, and run the project's tests and inspection commands before completion.

They reduce conflicts by assigning one agent to each task, requiring file locks, and checking project status before editing.

How HappyMonkeyAI/OpenUKPublicDataMCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HappyMonkeyAI/OpenUKPublicDataMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HappyMonkeyAI/OpenUKPublicDataMCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HappyMonkeyAI/OpenUKPublicDataMCP

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/happymonkeyai/openukpublicdatamcp/agents-md/github.svg)](https://agentmods.dev/instructions/happymonkeyai/openukpublicdatamcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/happymonkeyai/openukpublicdatamcp/agents-md"><img src="https://agentmods.dev/badge/instructions/happymonkeyai/openukpublicdatamcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/happymonkeyai/openukpublicdatamcp/agents-md"><img src="https://agentmods.dev/badge/instructions/happymonkeyai/openukpublicdatamcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 617 This file is loaded in full into every session.

When invoked 617 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00617	$0.00617
Opus 5.5	$0.00247	$0.00247
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00062	$0.00062

Measured 6d ago against content hash 9f6e569c6232, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OpenUKPublicDataMCP 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 6d ago.

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.

AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS — OpenUKPublicDataMCP

This repo uses Stephen's lightweight multi-agent coordination workflow for complex builds.

First actions

Read CONTEXT.md, HERMES.md, and relevant ADRs.
Check the task board:
```
python3 scripts/tasks.py list
```

Check lock state:

python3 scripts/update-status.py
cat .agent-status.md

Claim one unblocked task:

AGENT_ID=<agent-name> python3 scripts/tasks.py claim <task-id>

Lock files before editing:

AGENT_ID=<agent-name> python3 scripts/lock.py <file1> <file2> "<task>"

Coordination rules

One agent per task.
Do not edit files you have not locked.
Do not edit .agent-manifest.json, .agent-status.md, or .agent-tasks.json directly; use scripts.
If a lock is held by another agent, choose another task.
Keep changes minimal and focused.
Update README/CONTEXT/ADR/research notes when implementation decisions change.

Verification before completion

Run the relevant real checks before marking a task complete. For baseline work:

pytest
python -m compileall src tests
fastmcp inspect src/openukpublicdata_mcp/server.py:mcp
fastmcp list src/openukpublicdata_mcp/server.py --json

Then complete/unlock:

AGENT_ID=<agent-name> python3 scripts/tasks.py verify-complete <task-id>
AGENT_ID=<agent-name> python3 scripts/unlock.py <file1> <file2>

CLI swarm options

Hermes may coordinate direct CLI agents where useful: grok, opencode, agy, and other available coding CLIs. Give each a scoped task from .agent-tasks.json and require it to follow this file.

Session start and end (Spine) — ADR-0005

If the spine MCP is available, call session_brief(project="openuk-public-data-mcp") (or the absolute path of this repo) first and use get_section / recall instead of reading PROGRESS.md or CONTEXT.md whole. Without the MCP, run spine brief from the repo root. If neither works, ground normally — never block the session on Spine. Before you stop, call checkpoint with your agent name (e.g. hermes), what was done, what's next and any blockers. Save durable why/gotcha/decision facts with record_memory. Prefer checkpoint over free-form PROGRESS.md appends when Spine is available. Shared protocol law: HappyMonkeyAI AgentsProtocol (ADR-0005 Spine warm-start).

Read the full file on GitHub · 61 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.

6d ago Changed · +5 lines · +196 tokens per session 9f6e569c6232
2mo ago First seen · 56 lines · 421 tokens per session scan A 454f2c6a0a6f

Subscribe to this mod's changes

OpenUKPublicDataMCP AGENTS.md is an instructions file published in the GitHub repository HappyMonkeyAI/OpenUKPublicDataMCP (1 stars, last pushed 6d ago), licensed MIT. It adds 617 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

Building agents

OpenUKPublicDataMCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
OpenUKPublicDataMCP AGENTS.mdHappyMonkeyAI/OpenUKPublicDataMCP	Instructions file	1	6d ago	MIT	A	617	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

OpenUKPublicDataMCP: Instructions file for Codex