The task
Produce one reviewable output.
Start with the human version. Use AI if helpful. The goal is a short evidence pack a reviewer can inspect, not a private chat transcript.
Task
Turn one messy public document trail into a clean receipt card and publishable explanation.
Why it matters
Politics with receipts needs a repeatable desk, not heroic one-off thread archaeology.
What you produce
Receipt draft with claim, value if any, source, checked date, caveats, and why it matters.
Useful inputs
FOI responses, council papers, PDFs, meeting minutes, public datasets.
Steps
- Read the task.
- Gather public sources.
- Write the evidence pack.
- Add caveats.
- Submit or preview for review.
AI-assisted prompt
Ask your AI to help, then keep the claim inspectable.
You are working for Future Union.
Action brief: Receipts desk
Action URL: https://www.futureunion.org.uk/control-room/actions/receipts-desk/
Board lane: Needs backing
Parent mission: Check the claims
Time box: 90-180 minutes
Output type: Receipt draft
Mission:
Turn one messy public document trail into a clean receipt card and publishable explanation.
Why it matters:
Politics with receipts needs a repeatable desk, not heroic one-off thread archaeology.
Inputs:
FOI responses, council papers, PDFs, meeting minutes, public datasets.
Required output:
Receipt draft with claim, value if any, source, checked date, caveats, and why it matters.
Acceptance criteria:
Claim is narrow, source is public, uncertainty is named, and legal or personal-data risk is flagged before use.
Submission route:
Finish the evidence pack locally, then submit it for review straight from the runner — it sends the pack to Future Union for a human to check, and nothing becomes public without that review. A signed, publish-from-your-machine route is being tested and will sit on top of this.
Rules:
- Use public source links for every factual claim.
- Separate facts, interpretation, caveats, and recommended action.
- Do not invent data, quotes, people, organisations, or legal claims.
- Do not contact third parties, submit FOIs, scrape private systems, or process personal data unless a human explicitly tells you to.
- Include agent/tool, model if known, approximate tokens/runtime if available, and human edits.
- Return a clean Markdown evidence pack a human can review quickly.Run this with an AI agent (advanced)
For developers using Claude Code, Codex, or similar. This sets up the Future Union runner, creates a local workspace, and keeps publishing behind a preview step — nothing goes out without your confirmation.
Current safety boundary: the helper works from one mission folder and publish preview only includes allowlisted mission files. It is not yet a hardened OS sandbox, so use a separate OS user, container, or VM for untrusted agents.
curl -fsS https://www.futureunion.org.uk/agent-pack/fu-runner.sh -o fucr && FU_BASE_URL=https://www.futureunion.org.uk sh fucr mission receipts-deskNow
3 active runs
Review
Local work in progress
Evidence pack
No review score yet
Credited
0 people
Runner links
Feeds and network lane
Preview first. Publish second. The helper shows commits, score, benchmark command, and safety boundary before anything public.
./bin/fu-mission experiment-doctor ./bin/fu-mission experiment-publish