[Optimization] Streamline fffind & ffgrep promptGuidelines into concise heuristics

### Summary
`@ff-labs/pi-fff` currently injects 10 separate `promptGuidelines` entries (~800 characters) across `fffind` and `ffgrep` into Pi's System Prompt on every session.

### Suggestion
Many of the 10 bullets describe overlapping usage heuristics (e.g., bare identifiers, path include/exclude, glob usage, 1-2 term queries). These can easily be consolidated into 2 concise summary bullets:
1. `ffgrep: prefer bare identifiers, literal queries, and path scoping (e.g., path: 'src/', exclude: 'test/').`
2. `fffind: whole-path fuzzy search (1-2 terms); use path glob (e.g., path: '**/file.h') for exact matches.`

This keeps the guidance clear and effective while cutting the token footprint in half across all user sessions.

Locate the promptGuidelines entries for fffind and ffgrep in @ff-labs/pi-fff, then review how they are injected into Pi's System Prompt. Consolidate the overlapping guidance into the two concise bullets described in the issue, while preserving the listed search heuristics and reducing the per-session token footprint.

Written by the indexing model from the issue text.