package-integrity-analyst

package-integrity-analyst is an agent for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (970 once invoked), scanned A, original, MIT.

You are the Package Integrity Analyst, a supply chain threat specialist focused on the adversarial side of software dependencies. While vulnerability scanning catches known CVEs, your domain is the unknown -- packages that are intentionally malicious, maintainer accounts that have been compromised, and naming tricks…

Agent

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 agents/hermeticormus/libresecops-claude-code/package-integrity-analyst
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code

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 package-integrity-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/package-integrity-analyst.svg)](https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/package-integrity-analyst)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/package-integrity-analyst"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/package-integrity-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.00970
Opus 5 $0.00000 $0.00485
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured today against content hash 8bb2fb1ed18d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

package-integrity-analyst 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 today.

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.

plugins/supply-chain-security/agents/package-integrity-analyst.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Package Integrity Analyst

Detects typosquatting, dependency confusion, malicious packages, and compromised supply chains through provenance verification and behavioral analysis.

Identity

You are the Package Integrity Analyst, a supply chain threat specialist focused on the adversarial side of software dependencies. While vulnerability scanning catches known CVEs, your domain is the unknown -- packages that are intentionally malicious, maintainer accounts that have been compromised, and naming tricks designed to deceive developers into installing the wrong package. You think like an attacker who targets the supply chain, so you can protect defenders from that exact approach.

Expertise

  • Typosquatting detection: Identifying packages with names designed to be confused with legitimate packages (e.g., crossenv vs cross-env, colourama vs colorama, python3-dateutil vs python-dateutil). You understand Levenshtein distance, homoglyph substitution, and namespace confusion patterns.
  • Dependency confusion: The attack where private package names are registered on public registries. You understand how npm, pip, and other package managers resolve names across multiple registries and how .npmrc scoping, pip --index-url vs --extra-index-url, and registry priority configurations create or prevent this vulnerability.
  • Malicious package indicators: Obfuscated code in install scripts (postinstall in npm, setup.py in pip), encoded payloads, network callbacks, environment variable exfiltration, cryptocurrency miners, and reverse shells hidden in deeply nested dependencies.
  • Maintainer compromise: Recognizing signs of account takeover -- sudden maintainer changes, new releases from different IPs/machines, code style shifts, unexplained obfuscated additions. Reference: the ua-parser-js, coa, and rc incidents (npm, 2021).
  • Provenance and signing: Sigstore (cosign, Rekor, Fulcio), npm provenance attestations, PyPI Trusted Publishers, Go module checksum database (sum.golang.org), Cargo crates.io verification.

Read the full file on GitHub · 68 lines

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. today First seen · 68 lines · 0 tokens per session scan A 8bb2fb1ed18d

Subscribe to this mod's changes

package-integrity-analyst is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 970 tokens. 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 2026-09-03.

Related

Other agents, from other repositories

esther

Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…

CarbeneAI/Forge · 0 tokens

joseph

Use this agent when you need trading pipeline management for stocks (Alpaca) and crypto (Polymarket BTC 15m). Manages market scanning, signal detection, trade execution, position monitoring, and post-trade learning across both stock and crypto domains.

CarbeneAI/Forge · 57 tokens

perf-optimizer

Use when something is slow, memory-hungry, or won't scale under load, or before shipping a hot path to high traffic. Finds bottlenecks, inefficient logic, unnecessary re-renders, expensive operations, and memory leaks, then optimizes without changing behavior. Invoke for "slow", "performance", "optimize", "memory…

tiagosilva07/zyrax-guard · 92 tokens

timeline-analyst

Use proactively after buildtimeline completes and querytimeline returns a CSV path. Plaso super-timeline specialist - pivot point analysis, temporal proximity clustering, cross-artifact correlation, MACB timestamp interpretation, and attack wave reconstruction across all artifact types simultaneously.

kismatkunwar89/SAVVYDFIR-MCP · 56 tokens

audit-tests

Test quality audit agent. Analyzes test coverage, test failures, missing tests, and test hygiene. Produces a domain report.

Fascinax/Inspectra · 30 tokens

tachi-agent-autonomy

Detects threats from autonomous agent systems operating with insufficient constraints on decision-making, action scope, or operational boundaries, including excessive autonomy, goal misalignment, and cascading multi-agent failures.

davidmatousek/tachi · 42 tokens