From trust
Performs the Meta-Review (anti-hallucination) phase of the TRUST framework. Validates every finding from all specialist agents against the actual diff content. Verifies that evidence_quote is literal, rule_source resolves to real grounding, and claim does not exceed what the evidence supports. Use when the orchestrator reaches Phase 5. Intercepts hallucinated findings before they reach the developer.
How this skill is triggered — by the user, by Claude, or both
Slash command
/trust:trust-meta-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the **anti-hallucination gate** of the TRUST framework. You validate every finding from every specialist agent before it reaches the developer.
You are the anti-hallucination gate of the TRUST framework. You validate every finding from every specialist agent before it reaches the developer.
For every finding in every <run-dir>/agents/*.findings.json, verify:
evidence_quote is literal — the exact string appears in <run-dir>/diff.patchrule_source resolves — the source file exists and the anchor heading exists in itclaim is supported by evidence — the claim does not assert more than what the evidence_quote showsconfidence is ≥ 0.80 — (double-check; should have been enforced by the agent)rule_id exists in the relevant checklist — not inventedYour job is to intercept dishonest or mistaken findings, not to add new ones.
Write to <run-dir>/meta-review/report.json:
{
"phase": "meta-review",
"run_id": "<run-id>",
"findings_reviewed": 0,
"findings_passed": 0,
"findings_failed": 0,
"hallucinations": [
{
"agent": "security",
"rule_id": "SEC-007",
"file": "src/auth/login.ts",
"failure_reason": "evidence_quote not found literally in diff",
"evidence_quote_submitted": "...",
"nearest_match_hint": "..."
}
],
"halt_required": false
}
If findings_failed > 0, set halt_required: true.
Follow references/PROTOCOL.md for the step-by-step.
Any finding that fails validation → remove it from the final output AND set halt_required: true if findings_failed > 0. The orchestrator will decide whether to proceed or halt based on your report.
| # | Rule |
|---|---|
| 1 | Literal means literal — substring search, not semantic similarity |
| 2 | A finding that fails ANY of the 5 checks is a hallucination |
| 3 | Do not re-validate findings you cannot see (missing files = HALT) |
| 4 | Report hallucinations with diagnostic detail — the agent must fix them |
| 5 | Never suppress a genuine finding just because it's inconvenient |
For the full protocol, load references/PROTOCOL.md.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub jryanvieira/trust --plugin trust