Borrowing it
Nothing to install: this file belongs to Defend-AI-Tech-Inc/agent-discover-scanner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Defend-AI-Tech-Inc/agent-discover-scanner/main/CLAUDE.mdgit clone --depth 1 https://github.com/Defend-AI-Tech-Inc/agent-discover-scannerWrote 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.
[](https://agentmods.dev/instructions/defend-ai-tech-inc/agent-discover-scanner/claude-md)<a href="https://agentmods.dev/instructions/defend-ai-tech-inc/agent-discover-scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/defend-ai-tech-inc/agent-discover-scanner/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/defend-ai-tech-inc/agent-discover-scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/defend-ai-tech-inc/agent-discover-scanner/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03482 | $0.03482 |
| Opus 5 | $0.01741 | $0.01741 |
| Sonnet 5 | $0.00696 | $0.00696 |
| Haiku 4.5 | $0.00348 | $0.00348 |
Grade A, and why
agent-discover-scanner CLAUDE.md scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — AgentDiscover Scanner
Open-source AI agent discovery tool (v2.7.1) published on PyPI as agent-discover-scanner.
Part of the DefendAI platform for autonomous AI governance.
MIT licensed. Maintained by Mohamed Waseem / DefendAI.
What this project does
AgentDiscover Scanner discovers, classifies, and inventories autonomous AI agents running across an infrastructure. It runs five detection layers simultaneously and correlates them into a unified agent inventory with five classifications:
| Class | Meaning | Risk |
|---|---|---|
| GHOST | Runtime AI activity — no source code found | Critical |
| CONFIRMED | Detected in code AND observed running | High |
| UNKNOWN | Found in code, not yet observed at runtime | Medium |
| SHADOW AI | Known app using AI without governance | Medium |
| ZOMBIE | Was active, no longer observed | Low |
The GHOST classification is the core value proposition — it catches AI agents making live API calls with no corresponding source code, owner, or deployment record.
Repository layout
src/agent_discover_scanner/ # Main package
cli.py # Typer CLI entry point (all commands)
scan_runner.py # Shared execute_scan_all() implementation
scanner.py # File discovery / walk
visitor.py # ContextAwareVisitor — AST-based Python detection
signatures.py # SignatureRegistry + individual Signature subclasses
js_signatures.py # JavaScript/TypeScript detection (esprima)
correlator.py # CorrelationEngine — cross-layer agent identity
network_monitor.py # Layer 2 — psutil-based network observation
mcp_detector.py # MCP server detection (v2.4.0+)
high_risk_agents.py # OpenClaw / AutoGPT / BabyAGI detection (v2.4.0+)
known_apps.py # Three-tier known-app resolution
saas_detector.py # SaaS blast radius scoring
behavioral_patterns.py # ReAct loops, RAG patterns, multi-turn detection
aibom.py # CycloneDX 1.6-oriented AI BOM export (v2.5.0+)
audit_reports.py # ghost-agents.md, mcp-report.md, summary.md writers
sarif_output.py # SARIF generation for Layer 1
sbom_analyzer.py # requirements.txt / package.json scanning
platform.py # DefendAI platform upload
errors.py # ValidationError, CLI helpers
models/ # Pydantic data models
monitors/ # Layer 3 — K8s/Tetragon monitor
layer4/ # Layer 4 — osquery endpoint discovery
reports/ # Layer 4 report generation
detectors/ # Layer 5 — Cloud Audit detectors (v2.7.0+)
cloud_audit/ # Package: base ABC, AWS CloudTrail, Azure/GCP stubs
__init__.py # Auto-discovery + run_cloud_audit_detection()
base.py # CloudAuditDetector ABC + CloudAuditFinding dataclass
aws_cloudtrail.py # AWS CloudTrail + Lake — GA
azure_monitor.py # Azure Monitor — Preview stub
gcp_audit.py # GCP Cloud Audit Logs — Preview stub
cloudtrail.py # Backward-compat shim → re-exports from cloud_audit/
tests/ # pytest test suite
fixtures/ # Python/JS files used as detection test inputs
test_scanner.py
test_correlator.py
test_aibom.py
test_audit_bundle.py
test_behavioral_patterns.py
docs/ # Architecture diagrams, setup guides
deployment/ # systemd service, K8s Tetragon tracing policy
demo/ # K8s manifests + sample repo for local demo
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.
- 12d ago First seen · 266 lines · 3,482 tokens per session scan A ba657b3f51bc
agent-discover-scanner CLAUDE.md is an instructions file published in the GitHub repository Defend-AI-Tech-Inc/agent-discover-scanner (21 stars, last pushed 1mo ago), licensed MIT. It adds 3,482 tokens to every session, about $0.0174 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).