narco-check

$npx mdskill add open-gitagent/opengap/narco-check

Audits memory integrity to detect hallucinations and state poisoning.

  • Detects hallucinations, circular confirmations, and state poisoning in agent memory.
  • Uses OpenRouter with Claude Opus 4.6 as the auditor model.
  • Triggers after 2 consecutive failures or during nightly deep dive audits.
  • Runs grounding checks and outputs raw system state for verification.

SKILL.md

.github/skills/narco-checkView on GitHub ↗
---
name: narco-check
version: 1.0.0
description: >
  Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning.
  Runs automatically after 2 consecutive failures or at nightly deep dive.
  Uses Opus 4.6 as the auditor model.
---

# Narco-Check — Memory Integrity Audit

## When This Runs

1. **Failure trigger:** 2 consecutive failures on the same task or tool
2. **End-of-day trigger:** Nightly deep dive audit (~3 AM)

## Audit Model

Must use `openrouter/anthropic/claude-opus-4.6`. Never run narco-check on a tier-0 or tier-1 model.

```bash
openclaw agent --model openrouter/anthropic/claude-opus-4.6 \
  --message "$(cat ~/.openclaw/workspace/skills/narco-check/audit-prompt.md)" \
  --mode now
```

## 5-4-3-2-1 Grounding Check

Run this first — before reading any logs. Anchors the audit in real system state.

**5 — Run five commands, paste raw output verbatim:**
```bash
date
hostname
df -h /
docker ps --format "table {{.Names}}\t{{.Status}}"
cat ~/.openclaw/workspace/HEARTBEAT.md | head -3
```

**4 — Confirm four workspace files exist, paste first line:**
```bash
head -1 ~/.openclaw/workspace/IDENTITY.md
head -1 ~/.openclaw/workspace/SOUL.md
head -1 ~/.openclaw/workspace/MEMORY.md
head -1 ~/.openclaw/workspace/HEARTBEAT.md
```

**3 — Ping three endpoints, report HTTP codes:**
```bash
curl -s -o /dev/null -w "%{http_code}" http://localhost:18789/health
curl -s -o /dev/null -w "%{http_code}" --max-time 5 https://geniewars.com
curl -s -o /dev/null -w "%{http_code}" --max-time 5 https://siliconchimps.com
```

**2 — Run one Exa search, paste first real result:**
```bash
~/.openclaw/workspace/skills/exa-search/exa.sh "$(date +%Y) advance reader community" 2
```

**1 — State one provable fact:**
```
GROUNDED: [claim] — verified by [command] — output: [exact output]
```

A grounded check with failures is valid. A grounded check with fabricated output is **POISONED**.

## Audit States

- `CLEAN` — no failures, no audit triggered
- `DEGRADED` — issues found, state acceptable, resumed with different approach
- `POISONED` — contaminated entries found, stop and notify Ludo

If POISONED: mark affected MEMORY.md entries `[QUARANTINE YYYY-MM-DD]`, notify Ludo via Slack DM before proceeding.

More from open-gitagent/opengap

SkillDescription
compute-ladder>
create-agentCreates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.
document-reviewReviews financial documents (prospectuses, ADVs, marketing materials) for FINRA 2210 compliance, required disclosures, and balanced presentation. Use when reviewing financial statements, audit documents, regulatory filings, or when the user mentions compliance checks, financial audits, or document verification.
export-agentConverts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models formats, and imports from Claude, Cursor, and CrewAI projects. Use when the user wants to convert an agent, migrate to another framework, export to LangChain/AutoGen/CrewAI, or import from existing automation tools.
knowledge-retrievalSemantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)
manage-skillsSearches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages the skill lifecycle. Use when the user wants to find skills, add new capabilities, install a skill, browse available skills, create a custom skill, or manage the skills system.
packet-factory>
paper-searchAcademic paper search via Google Scholar using Serper API
regulatory-analysisAnalyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
run-agentConfigures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.