skills/budget/SKILL.md
Use when you need to view or manage workflow turn budgets and limits.
npx skillsauth add seokan-jeong/team-shinchan team-shinchan:budgetInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
View and manage turn budget for the active workflow.
/team-shinchan:budget # Show current budget status
/team-shinchan:budget --set total=200 # Set total turn budget
/team-shinchan:budget --set phase=50 # Set phase turn budget
/team-shinchan:budget --reset # Reset used counters to 0
/team-shinchan:budget --reset phase # Reset only phase counter
| Arg | Default | Description |
|-----|---------|-------------|
| (none) | — | Show current budget status table |
| --set total=N | — | Set total turn budget to N |
| --set phase=N | — | Set phase turn budget to N |
| --reset | — | Reset both used_total and used_phase to 0 |
| --reset phase | — | Reset only used_phase to 0 |
Look for .shinchan-docs/*/WORKFLOW_STATE.yaml files. Use the most recently modified one.
If no workflow state found:
No active workflow found.
Start a workflow with /team-shinchan:start to enable budget tracking.
If --set total=N or --set phase=N is provided:
budget section exists; create if missing:
budget:
total: 200
phase: 50
used_total: 0
used_phase: 0
total or phase) with the given value NBudget updated: {field} set to {N}
If --reset is provided:
--reset phase: set budget.used_phase to 0--reset (no qualifier): set both budget.used_total and budget.used_phase to 0Budget counters reset.
budget section:
No budget configured for this workflow.
Use /team-shinchan:budget --set total=200 to configure.
.shinchan-docs/.session-id.shinchan-docs/work-tracker.jsonl
tool_use, file_change, delegationeffective_total = budget.used_total + session_turns
effective_phase = budget.used_phase + session_turns
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Budget Status
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Metric | Used | Max | Pct | Status |
|--------------|------|-----|-------|---------|
| Total turns | {effective_total} | {total} | {pct}% | {status} |
| Phase turns | {effective_phase} | {phase} | {pct}% | {status} |
Session turns (current): {session_turns}
Accumulated (previous): total={used_total}, phase={used_phase}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Status values:
On Track — under 80%WARNING — 80% to 99%EXCEEDED — 100% or above--reset phase when advancing phases)development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
development
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.