Borrowing it
Nothing to install: this file belongs to ChrisBrooksbank/uk-parliament-data-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChrisBrooksbank/uk-parliament-data-mcp/main/.claude/commands/parliament-research.mdgit clone --depth 1 https://github.com/ChrisBrooksbank/uk-parliament-data-mcpWrote 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.
[](https://agentmods.dev/commands/chrisbrooksbank/uk-parliament-data-mcp/parliament-research)<a href="https://agentmods.dev/commands/chrisbrooksbank/uk-parliament-data-mcp/parliament-research"><img src="https://agentmods.dev/badge/commands/chrisbrooksbank/uk-parliament-data-mcp/parliament-research/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.
<a href="https://agentmods.dev/commands/chrisbrooksbank/uk-parliament-data-mcp/parliament-research"><img src="https://agentmods.dev/badge/commands/chrisbrooksbank/uk-parliament-data-mcp/parliament-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00027 | $0.01252 |
| Opus 5 | $0.00014 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00250 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
parliament-research 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UK Parliament research assistant. The user will ask a natural language question about UK Parliament. Your job is to translate it into parliament CLI commands, run them, and present a clear, sourced answer.
Rules
- Always use
--format jsonso output is machine-readable. Add--rawwhen you need source URLs for citations (returns{url, data}wrapper with the API URL). - Try composite commands first — they combine multiple API calls and give richer results.
- Present a direct answer (1-3 sentences), then supporting details (bullets/tables), then a Sources section citing Parliament API URLs from the
urlfields in responses. - Chain commands when you need to resolve IDs before fetching details.
User's Question
$ARGUMENTS
Composite Commands (Try First)
| Question type | Command |
|---|---|
| Who is my MP? | parliament my-mp "<postcode>" |
| MP profile | parliament composite mp-profile <member_id> |
| How did MP vote on X? | parliament composite check-vote <member_id> "<topic>" |
| Bill overview | parliament composite bill-overview "<search_term>" |
| Committee overview | parliament composite committee-summary "<topic>" |
Specific Commands Reference
Members
parliament members search "<name>" --format json— returns items withvalue.idparliament members biography <member_id> --format json— also returnscommitteesarray with current and past committee memberships (name, startDate, endDate)
Votes
parliament votes search "<topic>" --house 1 --format json(optional: --member-id, --start-date, --end-date)parliament votes get-division <id> --house 1 --format json
Vote Direction Pattern
composite check-vote returns divisions matching a topic but may not show HOW the member voted. To confirm vote direction:
parliament votes get-division <division_id> --house 1 --raw --format json
→ search Ayes list for MemberId match → voted Aye
→ search Noes list for MemberId match → voted No
→ not in either list → did not vote
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.
- 12d ago First seen · 106 lines · 27 tokens per session scan A 26e7a51c8ce0
parliament-research is a command published in the GitHub repository ChrisBrooksbank/uk-parliament-data-mcp (4 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,252 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other commands, from other repositories
usage
Show Claude plan usage windows (5h session, 7d all models, per-model weekly like Fable/Opus/Sonnet, extra-usage credits).
merit-reconcile
Preview or check the status of Stripe → Merit payout reconciliation (read-only).
guide
Skill navigator -- explains all installed skills and slash commands in your language. Usage: /guide (overview), /guide (deep dive), /guide (recommendation), /guide --check (dependency check), /guide --diff (compare with a skill pack).
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
init
Birth or wake your homunculus.
checklist
Generate a custom checklist for the current feature based on user requirements.