Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
TypeScript agentic-aiai-agentsai-codinganthropicautomationclaudeclaude-codecodexcoding-agentsdevops-automationdevtoolsgithub-actionsgrokllmloop-engineeringmcpprompt-engineering
name: loop-budget description: Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Loop Budget Guard
Run at the start and end of every loop iteration.
Start of run
- Read
loop-budget.mdfor daily caps and kill-switch flags. - Read recent entries in
loop-run-log.md(last 24h). - Sum
tokens_estimatefor the active pattern today. - If spend ≥ 80% of the pattern's daily cap → report-only mode (no sub-agents, no auto-fix).
- If spend ≥ 90% and High Priority items remain in
STATE.md, yield to the budget-negotiator skill (if installed). Otherwise, if spend ≥ 100% orloop-pause-allis set → exit immediately with a one-line note in STATE.md. - If watchlist/state has no actionable items → exit in <5k tokens (do not spawn sub-agents).
End of run
Append one JSON object to loop-run-log.md:
{
"run_id": "<ISO8601>",
"pattern": "<pattern-id>",
"duration_s": <number>,
"items_found": <number>,
"actions_taken": <number>,
"escalations": <number>,
"tokens_estimate": <number>,
"outcome": "no-op | report-only | fix-proposed | escalated"
}
Rules
- Never exceed
max sub-agent spawns/runfromloop-budget.md. - High-cadence patterns (CI Sweeper, PR Babysitter) must early-exit when nothing is actionable.
- On self-throttle, append a line to
loop-budget.mdunder Alerts This Period.