Files
Toju/agents-docs/AGENT_WORKFLOW.md
T
myxeliumandCursor cfe10907be chore: cut agent token burn with scoped bootstrap and handoffs
Slim always-on agent docs, default to toju-app plus targeted electron, and add HANDOFF.md plus a Cursor rule so long chats reset cleanly without agents opening new chats.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 21:49:06 +02:00

2.8 KiB
Raw Blame History

Agent Workflow & Operating Instructions

These rules apply to all AI agents working on this project.

Token budget (mandatory):

  • Default scope: toju-app/ + targeted electron/ + .gitea/workflows/ — see /AGENTS.md. No server/, e2e/, website/, docs-site/ unless the user expands scope.
  • Electron: follow the renderer → preload → one handler path; never dump the whole electron/ tree.
  • Prefer path-scoped search; one focused agent; no Bugbot / security / best-of-N unless asked.
  • Handoff > fat chats: agents cannot open new chats. Write agents-docs/HANDOFF.md and ask the user to start a new chat with that file attached.
  • Models: keep the users latest problem-solving model. Cut cost with scope + handoffs, not weaker models.

Do not re-read this whole file every turn after the first skim.


Workflow Orchestration

1. Plan only when ambiguity is real

  • Plan for unclear architecture or when the user asks.
  • Skip plan mode for focused, in-scope edits with clear acceptance criteria.

2. Subagents sparingly

  • Default: one agent.
  • Subagents only for true parallel search inside allowed paths.
  • Never spawn extra review agents unless the user asks.

3. Handoff / short sessions

Triggers: user says handoff / new chat; thread is long with more major work left; switching objectives.

Action: overwrite agents-docs/HANDOFF.md with Status: active (Goal, Completed, Changed files, Decisions, Failed approaches, Current issue, Next steps, Commands). Then stop major work and ask the user to open a new chat.

New chat: if handoff is active, read it first; continue Next steps; do not redo Completed work.

4. Self-Improvement Loop

At session start: LESSONS-INDEX.md only; open matching lesson bodies by tag.

Record a lesson + index line when corrected. Prefer fewer sharp rules (~20).

5. CONTEXT.md upkeep

Default: toju-app/CONTEXT.md. Read electron/CONTEXT.md only when touching Electron. Other packages only when in scope.

6. ADR upkeep

Only when hard-to-reverse + surprising + real trade-offs. Contract: agents-docs/AGENTS_ADRS.md.

7. Verification Before Done (behavior first)

Done = asked functionality works. Unit green ≠ done for product asks. Prefer in-scope proof; dont pull e2e/server “just to be sure.”

8. Demand Elegance (Balanced)

One pause for non-trivial design; skip for obvious fixes.

9. Autonomous Bug Fixing

Fix with evidence in default scope. If root cause is clearly server/ (or similar), say so and ask to expand scope.


Pull Requests

Gitea: git.azaaxin.com/myxelium/Toju. Branch <type>/<short-description>; PR with summary + test plan; Fixes #<n> / Relates to #<n>.


Core Principles

  • Simplicity First · No Laziness · Minimal Impact · Cheap Context · Default Scope Fence · Handoff Beats Fat Context