Subagent Research Reliability

Problem

Dispatching subagents for research has three silent failure modes. Each produces a confident result that is worth nothing, and they fail in dispatch order:

1. The findings are a dead letter. The agent researches correctly and answers in plain text. Plain text a subagent prints is not visible to the main session. The work exists in a transcript nobody reads. What arrives instead is an idle notification carrying no content, which reads like completion.
2. The agent can't actually search. Its tools: grant lacks WebSearch/WebFetch even though its description says "performs web research." It returns a no-op or fabricates citations from training data.
3. The agent returns claims that do not hold. Fabricated citations, CVE IDs, arXiv IDs and cross-references are the web case. The general case is wider: a misquoted rule, a line number dressed as a section, and — the dangerous one — a checked negative that is false, where the agent reports "zero hits across all five files" and one of the five hits.