drew/skate
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
skate/IDEAS.md
Drew Galbraith 3fd448d431 Add modal editing to the agent TUI. (#2) 
Adds a status line indicating which mode the user is in.
Adds a "normal" mode with keyboard shortcuts (including a chorded shortcut 'gg').
Adds a command mode with several basic commands that can be entered into an overlay.

Chores:
- Cleans up design/claude/plan.md to avoid confusing claude.
- Adds some TODOs based on claude feedback.`

Reviewed-on: #2
Co-authored-by: Drew Galbraith <drew@tiramisu.one>
Co-committed-by: Drew Galbraith <drew@tiramisu.one>
2026-02-25 01:16:16 +00:00

2.2 KiB
Raw Permalink Blame History

IDEAS

Notes based on ideas I've had.

Token Usage Visualization

  • Per-turn token breakdown (input/output/cache) inline in conversation
  • Cumulative session totals in status bar
  • Estimated Cost of Usage

Planning Mode

  • Activity mode distinction in TUI (Plan vs Execute), visible in status bar
  • Planner agent: has tool access (reads, search) but no write/exec permissions
  • Plan output as structured markdown (steps, files, acceptance criteria)
  • :edit-plan command to open plan in $EDITOR before execution
  • Explicit plan approval gate before transitioning to execution
  • Executor agent spawned with plan file + project context (not planning conversation)
  • Plan-step progress tracking (complete/in-progress/failed) visible in TUI
  • Done when: Can plan a task, review/edit the plan, then execute it as a separate activity

Sub-Agents

  • spawn_agent tool, independent ConversationTree per sub-agent
  • Agent tree sidebar in TUI, navigable in Normal mode
  • Sub-agents follow same approval policy with hard deny on unpermitted actions
  • Plan executor refactored as a sub-agent specialization
  • Done when: Agent delegates to sub-agent, user can inspect it, result flows back

Context Window Management

  • Token counting for outgoing payloads
  • Compaction strategy: summarize older turns, preserve full history in session log
  • Stable message prefix for prompt caching
  • Done when: Conversations run indefinitely without hitting context limits

Automated Anomaly Notation

Defered TODO list

  • Allow the user to notate things that should be fixed after the agent has iterated on its full loop.
  • Potentially add a way to iterate through the todo list at the end.

Session Logging

  • JSONL SessionWriter with Event structure
  • Parent IDs, timestamps, token usage per event
  • Predictable file location with session IDs
  • Ability to resume prior session.
  • Done when: Session files are coherent, parseable, with token counts per turn

Which-key like help

  • Show command chording in normal mode.
  • Help window slides up from bottom of screen.