offload-analyst: stop recursively re-delegating the whole audit to itself

commands/offload-audit.md tells a heavy-target caller to hand the work to
Agent(offload-analyst). Nothing told the analyst it IS that delegation target,
so on a large plugin it re-judged the target heavy by the same criteria and
spawned another offload-analyst instance, which did the same again — observed
live against the cluster plugin (11 agents, ~27 skills), 3-4 levels deep, each
restarting the same early measurement steps with no forward progress.

Fixed by making the analyst explicit that its only Agent calls are the fixed
filing chain, and scoping the command's delegation guidance to the top level
only.

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
 	"name": "inference-arbitrage",
-	"version": "0.4.0",
+	"version": "0.4.1",
 	"description": "Audits a Claude Code plugin's definitions and usage transcripts to find steps that should be a deterministic script instead of raw LLM inference, and files the well-evidenced ones as issues on the target repo.",
 	"author": {
 		"name": "oleks"

agents/offload-analyst.md

@@ -31,6 +31,19 @@ ${CLAUDE_PLUGIN_ROOT}/bin/offload-scan --plugin <name> --days N --json  # dynami
 
 ## What you never do
 
+- **You are the delegation target — never re-delegate the whole audit.** If you
+  were spawned via `Agent(subagent_type="inference-arbitrage:offload-analyst")`
+  because a caller judged the target heavy, that call already happened. Reading
+  a large target's inventory/scan output, or the `offload-audit` skill's own
+  "for a heavy target, hand the work to `Agent(offload-analyst)`" line, is not a
+  reason to spawn another instance of yourself — that line describes what a
+  *caller* does before reaching you, not what you do once you are the one doing
+  the work. The only `Agent` calls you ever make are the fixed filing chain
+  (`Agent(anxious:issuer-agent)` → `cluster:gitea-agent`, §7 below) — never
+  another `offload-analyst`, and never another `offload-audit` skill invocation
+  once you have already loaded it once. A target being large (many skills or
+  agents) is a reason to work through it methodically, not a reason to hand it
+  to a fresh copy of yourself with no memory of what you've already measured.
 - **Never edit the plugin you audit.** Read-only, always. This separation is what
   preserves your ability to conclude "no offload here" — an auditor that writes
   the code it recommends cannot credibly decline to recommend.

commands/offload-audit.md

@@ -18,7 +18,11 @@ Run the full audit on **$ARGUMENTS**.
    previous window, FR-4.5) and the marker search. For a heavy target, or when
    the report should not consume this session's context, hand the work to
    `Agent(subagent_type="inference-arbitrage:offload-analyst")` instead — one
-   agent for the whole audit, never one per skill (spec §7).
+   agent for the whole audit, never one per skill (spec §7). **This delegation
+   happens at most once, from this top-level command to the analyst.** The
+   analyst instance you spawn is the delegation target, not another decision
+   point — it never re-delegates the whole audit to a further `offload-analyst`
+   instance, however large the target looks from inside.
 
 Filing is implicit: a candidate that clears the rubric gate and the value
 threshold is filed without asking. Everything below the gate is reported as a