Narco-Check

by open-gitagent

Narco-Check is an AI Engineering skill for Claude Code, published by open-gitagent in opengap.

2.9K stars346 forkson open-gitagent/opengapAdded 2026/08/17Repository updated 2026/07/02

View source on GitHub Download repo ZIP

agentagent-frameworkagent-skillsagentsassistantclaude-codegitagentopen-standardopenclawskills

Install in seconds

Install Narco-Check

Copy Narco-Check into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/open-gitagent/opengap/tree/main/examples/jason-my-claw-is-the-law-deebee-4567b4/skills/narco-check ~/.claude/skills/narco-check

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/open-gitagent/opengap.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: examples/jason-my-claw-is-the-law-deebee-4567b4/skills/narco-check/SKILL.md in open-gitagent/opengap
Installs to: ~/.claude/skills/narco-check
Collection: One of 18 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Narco-Check does

Narco-Check audits an agent's memory for hallucinations, circular confirmations, and state poisoning when triggered by repeated failures or the nightly deep dive. It grounds checks in real system state and flags poisoned memory entries before proceeding.

Narco-Check is cataloged under AI Engineering on DirSkills. Narco-Check comes from a repository tagged agent, agent-framework, agent-skills, agents and assistant.

Documentation

README

Excerpt

Narco-Check — Memory Integrity Audit

When This Runs

Failure trigger: 2 consecutive failures on the same task or tool
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

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Narco-Check

What else does open-gitagent publish alongside Narco-Check?
Narco-Check is one of 18 skills that DirSkills catalogs from open-gitagent/opengap, the repository it ships in. Its siblings there include Code Review, Compute Ladder and Create Agent. Each one is a separate skill with its own page in this directory, installs the same way Narco-Check does, and is maintained by open-gitagent in that same repository. The rest of the collection is listed on the open-gitagent/opengap page.
How does Narco-Check compare to other AI Engineering skills?
Narco-Check ranks #704 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Narco-Check against them. Open each page to compare what they document and how they install.