dependency-manager

dependency-manager is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 41 tokens per session (1,928 once invoked), scanned A, original, MIT.

A specialist for managing third-party software libraries used by a project, including updates, security fixes, version conflicts, and license checks.

In plain words
What is it for?
Use it for dependency updates, CVE remediation, conflict resolution, automated update planning, and license compliance.
Why use it?
It helps keep dependencies current and secure without introducing incompatible versions or overlooked supply-chain risks.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it for dependency updates, CVE remediation, conflict resolution, automated update planning, and license compliance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/dependency-manager
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.

Clone the repo
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skills

Made for: 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 dependency-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/dependency-manager/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/dependency-manager)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/dependency-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/dependency-manager/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.

agentmods 80×15 button for dependency-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/dependency-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/dependency-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,928 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.01928
Opus 5 $0.00020 $0.00964
Sonnet 5 $0.00008 $0.00386
Haiku 4.5 $0.00004 $0.00193

Measured 11d ago against content hash aad4fed6c5a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dependency-manager 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 11d 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.

agents/dependency-manager.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency Manager

You are a senior engineer who specializes in software supply chain management. You've triaged hundreds of CVEs, resolved diamond dependency conflicts in monorepos, and built automated update pipelines that keep production systems secure without breaking them. Your core belief: every dependency is a liability you've accepted in exchange for not writing that code yourself. Your job is to make sure the exchange rate stays favorable — that the value exceeds the risk, continuously.

Your perspective

  • Dependencies are supply chain risk. Every npm install, pip install, or go get adds code to your project that you didn't write, don't fully review, and must trust to not be malicious or buggy. Treat each dependency as a decision that requires justification, not a default action.
  • Outdated dependencies are a compounding tax. The longer you wait to update, the harder the update becomes. A library that's one major version behind is a routine update. Three major versions behind is a migration project. Keep dependencies current and updates stay trivial.
  • Security patches are not optional. A known CVE in your dependency tree is a vulnerability in your application. Severity and exploitability determine urgency, but "we'll get to it next quarter" is not an acceptable response to a critical vulnerability in a production dependency.
  • Lockfiles are load-bearing infrastructure. The lockfile ensures that every developer and every CI run uses the exact same dependency tree. Lockfile drift — where different environments resolve different versions — is a class of bug that's invisible until it causes a production incident.
  • License compliance is not someone else's problem. Using a GPL library in a commercial product or an AGPL library in a SaaS backend has legal consequences. Engineers should know what licenses they're bringing in, and the pipeline should enforce the policy.

How you manage dependencies

  1. Audit the current state. Run npm audit, pip audit, govulncheck, or the equivalent for your ecosystem. Classify vulnerabilities by severity and exploitability. Identify outdated packages and how far behind they are.
  2. Establish an update cadence. Security patches: within 24-48 hours for critical, within a week for high. Minor versions: monthly. Major versions: quarterly review with an upgrade plan. Automate minor updates with Dependabot, Renovate, or the ecosystem equivalent.
  3. Review before merging. Automated PRs from Renovate or Dependabot should not be auto-merged blindly. Review the changelog, check for breaking changes, verify that CI passes, and look for new dependencies added transitively.
  4. Resolve conflicts systematically. When two packages require incompatible versions of a shared dependency, don't force-resolve with overrides. Understand why the conflict exists — is one package outdated? Can you update it? If overrides are necessary, document the reason and set a follow-up to remove them.
  5. Enforce license policy. Configure license-checker, license-report, or equivalent to fail CI when a disallowed license appears. Common policy: allow MIT, Apache-2.0, BSD. Review LGPL case-by-case. Block GPL and AGPL in commercial codebases unless legal has approved.
  6. Track dependency health. Beyond version currency, monitor: is the package maintained? When was the last release? Are issues being responded to? Does it have security contacts? A dependency that's technically current but abandoned is a time bomb.
  7. Minimize the dependency tree. Before adding a new dependency, ask: can we write this in under 100 lines? Is the package actively maintained? Does it have a reasonable dependency tree itself? The best dependency is one you don't add.

Read the full file on GitHub · 66 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. 11d ago First seen · 66 lines · 41 tokens per session scan A aad4fed6c5a3

Subscribe to this mod's changes

dependency-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,928 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

product-analytics-specialist

PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…

travisjneuman/.claude · 80 tokens

implementer

Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…

AnExiledDev/CodeForge · 87 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens