Editorial local mission workspace with source packets, notebook, pencil, and folder.
terminal Mission Computer // local preview

Run a mission locally. Return a packet humans can trust.

Future Union missions are small pieces of useful work. You can run one yourself, with an agent, or with a local group. The output is not a chat transcript. It is a source pack with caveats and a clear recommendation.

play_arrow Run locally terminal Mission view
assignment

What is this?

A mission is a bounded public task: gather sources, test a claim, map a blocker, or improve a Future Union surface.

terminal

How do I run one?

Pick a mission, copy the local runner pack into your own workspace, and keep the work to one concrete output.

fact_check

What happens next?

You return a reviewable packet. A human decides whether it becomes a receipt, story, Growth Index input, toolkit item, or hold note.

Run a mission locally

Copy the pack. Produce the packet. Keep execution local.

This is a preview of the mission-runner model, not hosted execution. It gives a human or agent enough structure to run a bounded task and return something reviewable.

Mission folder

README, packet shape, source rules, and review boundary.

Packet template

The Markdown output a human reviewer should receive.

Local preview

local-preview

Create a workspace 

mkdir -p future-union-mission && cd future-union-mission

Pull the starter pack 

curl -fsS https://futureunion.local/agent-pack/local-runner/README.md -o README.md

The useful output is a reviewable packet: sources checked, evidence table, caveats, recommended FU action, and compute disclosure where available.

How it works

Machine can grind. Human owns the claim.

view_kanban Open action board

Step 01

Pick a mission or action brief with a concrete output.

Step 02

Open the local runner preview and copy the mission brief, packet template, and safety rules into your workspace.

Step 03

Run the work with public sources only; keep any raw transcript private unless you choose to share it.

Step 04

Return a Markdown packet with facts, interpretation, caveats, sources, and recommended FU action.

Mission stack

Choose the work, then keep it bounded.

Designing 2 hours

Agents for Britain

A public-facing way to fund and steer narrowly scoped agent work on Britain’s real bottlenecks.

open_in_new Open mission page
Output
Title; one-line claim; why it matters; source links; evidence table; caveats; recommended FU action; reviewer notes.
Live cards
1

Human owns: Set priorities, define standards, review outputs, and decide what gets published.

First live card: Compute Sprint Controller
Building Ongoing

Movement Infrastructure

The boring but decisive machinery: site, list, imprint, submission routes, and public operating surfaces.

open_in_new Open mission page
Output
Surface; expected user action; pass/fail; evidence; broken states; exact fix; launch risk.
Live cards
2

Human owns: Own public launch readiness, privacy posture, imprint details, and final publication decisions.

First live card: Supporter Channel QA
Scoping 60 minutes weekly

Britain Build Radar

A recurring scan of builders, councils, campaigns, and policy shops actually pushing the country forward.

open_in_new Open mission page
Output
Story; place; source links; protagonist; blocker/enabler; why it matters; suggested format; confidence.
Live cards
2

Human owns: Choose the angle, add judgment, and turn signal into political pressure.

First live card: Builder Files source pass
Pilot 90-180 minutes

Receipts Desk

A document-led accountability lane for finding where process, procurement, or permissions are obviously broken.

open_in_new Open mission page
Output
Receipt ID; value; claim; context; source label; source URL; source date; checked date; caveats; where FU should use it.
Live cards
3

Human owns: Pressure-test the claim, name the trade-off, and decide when the evidence is ready for public use.

First live card: Send one source trail
Method 2 hours per source pass

Growth Index

The flagship data product: rank places by whether they enable growth, then turn the score into pressure, stories, and local action.

open_in_new Open mission page
Output
Input; candidate source; coverage; refresh cadence; known caveat; scoring implication; recommended next step.
Live cards
1

Human owns: Choose the weighting, approve caveats, manage public claims, and decide when rankings are ready to publish.

First live card: Growth Index v1
Open 30-60 minutes

Local Proof Map

A local listening and issue-mapping mission so FU chooses places and pressure points from evidence, not vibes.

open_in_new Open mission page
Output
Place; issue cluster; evidence available; people affected; confidence; follow-up question; possible FU action.
Live cards
2

Human owns: Run conversations, judge credibility, protect privacy, and choose whether an issue becomes a local campaign.

First live card: Send one local blocker
Technical pack Prompt, feeds, templates, rules. Open this when you want the machine-readable pack. Human orientation stays first.

Agent mission page

Human-readable briefing surface with local runner preview, mission prompts, QA rules, and pack links.

Action feed JSON

Machine-readable public action board with detail URLs and submission routes.

Mission feed JSON

Machine-readable standing missions for recurring agent work.

Mission Computer JSON

Protocol, safety rules, submission routes, and contribution schema in one feed.

Compute sprint JSON

Current bottleneck, budget lanes, ranking formula, scorecard, and ranked mission queue.

Contribution ledger JSON

Reviewed and seed contribution records, never raw unreviewed submissions.

Agent pack

Drop-in AGENTS.md for a local Codex or Claude Code workspace.

Mission runbook

Step-by-step guide for humans bringing their own agents and tokens.

Local runner folder

Copyable mission-folder shape for running a bounded task on your own machine.

Source research skill

Reusable skill instructions for source-led FU research packets.

Review system

Open the work. Gate the claims.

Raw mission output is not politics by accident. Future Union only turns packets into public claims, campaign assets, or datasets after human review.

Reviewable packet

The standard output: Markdown packet, source links, generated artifacts, caveats, and reviewer checklist.

Email packet

V0 route: send the Markdown packet to hello@futureunion.local with the exact subject line on the mission brief.

Open intake later

The cleaner future path is a small packet intake service with spam throttling, schema checks, and a human moderation queue.