Verify Claim

Verify Claim (output-action divergence check)

Compare an agent's stated outcome against actual state. Returns one of: STATEMATCHESCLAIM (agent told the truth), STATEUNCHANGED (claimed action but nothing happened), STATEVIOLATEDCONSTRAINT (action happened but violated stated constraint), STATEMISMATCH (action happened but differently than claimed).

What to do

1. Parse $ARGUMENTS for the claim text. The first quoted string is the claim. Optional --before-snapshot= argument loads a previously-captured before-snapshot if available.
2. If no before-snapshot is provided, attempt to infer one from recent context: check git log, recent file mtimes, recent test runs.
3. Call mcp__openclaw-output-vetter__verify_action_outcome with:

• claim: the claim text
• before_snapshot: the loaded snapshot (or empty if inferring from current state)
• after_snapshot: take fresh snapshot of relevant paths NOW

1. Render the verdict.

Verdict rendering

STATEMATCHESCLAIM (agent told the truth)

> ✅ **VERIFIED** — claim matches actual state
> **Claim:** ""
> **Evidence:**
> - 
> - 
> **Confidence:** HIGH/MEDIUM/LOW based on snapshot completeness

STATE_UNCHANGED (action claimed but nothing happened)

> 🔴 **UNCHANGED** — claim says action happened, state shows it didn't
> **Claim:** ""
> **What's missing:**
> - 
> - 
> **What likely happened:** 
> **Action:** Re-run the action, watch for hook / permission / sandbox errors. Run `/aufgaard:verify-claim` again after.

STATEVIOLATEDCONSTRAINT (Codex-style)

> 🔴 **CONSTRAINT VIOLATED** — agent acknowledged a constraint then violated it
> **Claim:** ""
> **Stated constraint:** 
> **Actual violation:** 
> **Severity:** CRITICAL — this is the alignment-relevant failure mode
> **Action:** Roll back the unauthorized changes via `git restore`. Investigate why the constraint was violated — sandbox-escape bug? prompt overrride? agent-config attack? Use `/aufgaard:vet-config` on agent-config files to rule out poisoning.

STATE_MISMATCH (action happened but not as claimed)

> 🟡 **MISMATCH** — action happened, but differently than claimed
> **Claim:** ""
> **What's different:**
> - 
> **Likely cause:** 
> **Action:** Reconcile — either accept the actual state and update downstream consumers, or roll back and try the original claim again.

ACTION_OUTCOME rule families (8 rules in output-vetter v1.1+)

• ACTIONOUTCOME.STATEUNCHANGED — claimed action, no diff
• ACTIONOUTCOME.STATEVIOLATED_CONSTRAINT — read-only / sandbox / approval-gate breached
• ACTIONOUTCOME.MISSINGFILE — claim references a file that doesn't exist
• ACTIONOUTCOME.MISSINGCOMMIT — claim references commit that's not in git log
• ACTIONOUTCOME.MISSINGTEST_RESULT — claim "tests pass" but no test run found
• ACTIONOUTCOME.PARTIALDIFF — diff exists but doesn't include claimed changes
• ACTIONOUTCOME.UNINTENDEDDIFF — diff includes changes outside claimed scope
• ACTIONOUTCOME.SCOPEDRIFT — actual scope of change is wider than claimed

Cite the actual rule returned. The catalog above is reference.

Style notes

• Be specific about the evidence. "git log has no commits" beats "git status looks unchanged."
• For STATEVIOLATEDCONSTRAINT, treat as CRITICAL and recommend immediate rollback. This is the chiefofautism / Codex-class incident pattern.
• For STATE_UNCHANGED, the most useful diagnostic is usually "did a hook / permission / sandbox block the action silently?" — bias the recommendation toward checking those layers.

Edge cases

• If no before-snapshot can be inferred (fresh session, no recent activity), state: "No before-snapshot available. Verifying against current state alone — limited confidence. For higher confidence on future verifies, the PreToolUse hook captures snapshots automatically when the plugin is fully active."
• If $ARGUMENTS is empty: "Pass the agent's claim as a quoted argument: /aufgaard:verify-claim 'I committed the fix and pushed to main'"
• If output-vetter MCP not loaded: "output-vetter MCP not available. Verify pip install openclaw-output-vetter-mcp and the plugin is loaded."
• If the claim is too vague to verify (e.g. "I improved the code"), respond: "The claim is too vague for state-based verification. Re-ask the agent to state a specific verifiable claim — file modified, commit hash, test name passed, etc."

Footer CTA

---
Output-action divergence (P6.y) is one of 35 documented production-AI failure patterns. The [Production-AI MCP Suite Bundle](https://temurah.gumroad.com/l/production-ai-mcp-suite) ($29) includes the 8-page Field Reference PDF — covers the chiefofautism viral case + Codex sandbox-escalation + 698 real-world scheming incidents from the CLTR study (Oct 2025 - Mar 2026).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: temurkhan13
• Source: temurkhan13/aufgaard
• License: MIT

Install and usage instructions live in the source repository linked above.