feat(projman): add token usage estimation reporting
- New skill: token-budget-report.md with MCP overhead and skill loading estimation model based on known file sizes and static overhead tables - Sprint-plan displays token report after planning complete - Sprint-close displays token report after lessons captured - Visual-output.md updated with token report format - .gitignore exception for token-budget-report.md (not API tokens) Helps identify which phases and components consume the most context budget. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
@@ -99,3 +99,22 @@ For domain gate results displayed by orchestrator:
|
||||
| Hourglass | In progress |
|
||||
| Empty box | Pending / Not started |
|
||||
| Warning | Warning |
|
||||
|
||||
---
|
||||
|
||||
## Token Budget Report
|
||||
|
||||
Displayed at end of planning and closing phases:
|
||||
|
||||
```
|
||||
+-- Token Budget Report -----------------------------------------------+
|
||||
| Phase: [PHASE NAME] |
|
||||
| Sprint: [Sprint Name] |
|
||||
+----------------------------------------------------------------------+
|
||||
| MCP Overhead: ~XX,XXX tk |
|
||||
| Phase Cost: ~X,XXX tk (skills: N, agent: model) |
|
||||
| Est. Total: ~XX,XXX tk (~XX% of budget) |
|
||||
+----------------------------------------------------------------------+
|
||||
```
|
||||
|
||||
See `skills/token-budget-report.md` for full format and estimation model.
|
||||
|
||||
Reference in New Issue
Block a user