offload-audit: offload-analyst recursively re-delegates to itself on heavy targets — no base case #13
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Why: The offload-analyst agent currently has no guardrail preventing it from re-delegating the whole-audit task to another offload-analyst instance. This creates unbounded recursive self-delegation with no base case, causing token burn and preventing forward progress.
Problem:
commands/offload-audit.mdstep 3 directs heavy targets toAgent(subagent_type="inference-arbitrage:offload-analyst")agents/offload-analyst.mdcarries tools includingAgentand instructions to read/followoffload-audit/SKILL.mdObserved (2026-07-29): User ran
/offload-audit cluster(11 agents, ~27 skills). Main session delegated to offload-analyst → analyst loaded skill, re-measured, re-delegated to fresh offload-analyst → repeat, each level restarting early measurement/exploration without forward progress.Acceptance:
/offload-audit clusterand confirm single Agent(offload-analyst) call, no re-delegation chainLinks: Spec §7 (spec/inference-arbitrage.md)
Fixed by commit
06cb5b8on main.agents/offload-analyst.mdnow explicitly states the analyst is the delegation target and its only Agent calls are the fixed filing chain.commands/offload-audit.mdnow scopes the "delegate to offload-analyst" instruction to fire once, at the top level only, never recursively. Plugin bumped 0.4.0 → 0.4.1.Fixed by commit
06cb5b8on main.agents/offload-analyst.mdnow explicitly states the analyst is the delegation target and its only Agent calls are the fixed filing chain.commands/offload-audit.mdnow scopes the "delegate to offload-analyst" instruction to fire once, at the top level only, never recursively. Plugin bumped 0.4.0 → 0.4.1.