Rank by relevance

The budget goes to what the task touches.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule

Implement ranking to decide what the map shows. Signals to combine: TASK RELEVANCE - lexical/semantic match between the task description (and conversation so far) and file paths + symbol names; GRAPH CENTRALITY - files imported/referenced by many others rank higher (build a light import graph; a PageRank-style pass over it is the proven approach); RECENCY - recently edited or recently discussed files get a boost; CHAT MENTIONS - files already in the conversation rank highest. Output a scored file ordering per request. Test with three task descriptions against my repo and eyeball the top-10 per task - the relevant subsystem should dominate each list.

Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

Task-conditioned file ranking passing the three-task eyeball test.

Should NOT happen

An existing feature broke
A button only logs to console
Data disappears after refresh
Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Your notes for this step

Track what changed, failed, or needs follow-up. Notes export with the flow.

Pass the Verify Gate to complete this step

Verify before continuing

Do not move on until every check is true. The complete button stays locked until then.

Import-graph centrality computedTask text drives per-request scoresTop-10 lists match human judgment

Do not continue if…

! Dumping the file tree and calling it a map - names without symbols barely orient
! Unranked maps where the budget is spent alphabetically instead of relevantly
! Stale maps confidently pointing at moved or deleted symbols
! Maps so large they recreate the raw-dump problem they were meant to solve

If the AI messes this up

Use this when:

- it only made visual forms or placeholder UI
- buttons do nothing or only log to console
- data is not persisted - state disappears on refresh
- something that worked before is now broken

Use this when the AI fakes progress or breaks the feature. It forces a real fix.

Rankings ignore the task. Check the task-relevance signal weight - centrality alone produces the same map for every request; the combination is what makes the map task-aware.