narco-check

narco-check is a skill for Claude Code, Codex from open-gitagent/opengap. It costs 45 tokens per session (659 once invoked), scanned A, original, MIT.

A memory-integrity audit for an AI system. It checks for invented information, circular agreement, and corrupted system state after repeated failures or during a scheduled deep review.

In plain words
What is it for?
Use it after two consecutive failures on the same task or during a nightly audit. It helps verify workspace files, running services, disk state, and selected endpoints.
Why use it?
It provides a structured way to verify that the system's stored instructions and environment still match reality. The audit uses direct checks of files, services, containers, and network endpoints.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/open-gitagent/opengap/narco-check
Any agent
npx skills add open-gitagent/opengap --skill narco-check
Clone the repo
git clone --depth 1 https://github.com/open-gitagent/opengap

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for narco-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-gitagent/opengap/narco-check.svg)](https://agentmods.dev/skills/open-gitagent/opengap/narco-check)
Your own site
<a href="https://agentmods.dev/skills/open-gitagent/opengap/narco-check"><img src="https://agentmods.dev/badge/skills/open-gitagent/opengap/narco-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00659
Opus 5 $0.00023 $0.00329
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 4d ago against content hash 0800f2da3fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

narco-check scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}" http://localhost:18789/health
examples/jason-my-claw-is-the-law-deebee-4567b4/skills/narco-check/SKILL.md · 74 lines

What it actually says

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.

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:

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:

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:

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:

~/.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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 74 lines · 45 tokens per session scan A 0800f2da3fb1

Subscribe to this mod's changes

narco-check is a skill published in the GitHub repository open-gitagent/opengap (2,925 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 659 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories