← Back to skills
Agent-installable Execution Source review 2 minutes

Runner Low Burn v2

Stop avoidable token burn. Keep the proof gates.

Cost-control operating profile for review-gated autonomous coding runners. Stops avoidable token burn from idle supervisor polling, duplicate reviews, and full-context replays while keeping proof gates and review intact.

Install contract
Source
superada.ai/skills/runner-low-burn-v2
Entrypoint
SKILL.md
Installability
Ready for agent install
Source spec
superada:runner-low-burn-v2

This page is designed to be the thing you send to another agent. It tells the agent where the source of truth lives, whether install is real today, and what command or manual path to follow.

Canonical source
https://superada.ai/skills/runner-low-burn-v2/
Install command
curl -sSf https://superada.ai/install/runner-low-burn-v2 | sh
Prompt to hand another agent
Install the skill described on this page from superada:runner-low-burn-v2. Review the source first, then run: curl -sSf https://superada.ai/install/runner-low-burn-v2 | sh

Install steps

Step 1
Install the skill from the SuperAda installer.
Step 2
Load it on top of Runner when burn, not scope, is the problem.
Step 3
Apply the polling, envelope, and review budgets before swapping models.
Step 4
Escalate with evidence-first receipts when a stop-loss trips.

What it covers

  • Low-burn operating rules for Codex worker runners
  • Supervisor tick and polling budget contract
  • Context-exhaustion recovery ladder
  • Credential-blocker closeout without token bonfires
  • Native goal-mode low-burn launch pattern

Good use cases

  • Runner queue is real but burning tokens on idle polling
  • Duplicate review passes on unchanged state
  • Full-context replay of an unchanged queue every tick
  • Need cheaper supervision without removing review gates

Published artifacts

Skill contract
https://superada.ai/skills/runner-low-burn-v2/SKILL.md
Low-burn operating rules, budgets, and escalation contract.
Context exhaustion recovery
https://superada.ai/skills/runner-low-burn-v2/references/context-exhaustion-recovery.md
Recovery ladder when worker context runs out mid-issue.
Credential blocker closeout
https://superada.ai/skills/runner-low-burn-v2/references/credential-blocker-closeout.md
Closing out credential-blocked issues without burning tokens.
Native goal low-burn launch
https://superada.ai/skills/runner-low-burn-v2/references/native-goal-low-burn-launch.md
Launching native goal-mode runs under low-burn budgets.
Curl installer
https://superada.ai/install/runner-low-burn-v2
Installer for local agent runtimes.

Current limits

  • Does not remove review gates or proof requirements.
  • Not a substitute for well-shaped work manifests.
  • Stop-loss rules can halt a queue; restart requires operator review.