dependency-review

dependency-review is a skill for Claude Code from olgaiv39/claude-oss-skills. It costs 73 tokens per session (1,140 once invoked), scanned A, original, MIT.

A review guide for deciding whether a proposed software package should be added to a public open-source project. It compares alternatives, maintenance, licensing, supply-chain risk, and effects on the project.

In plain words
What is it for?
Assessing new runtime or development packages before installation and choosing whether to add them.
Why use it?
It helps prevent unnecessary dependencies and the extra security, maintenance, and resource costs they can bring.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Assessing new runtime or development packages before installation and choosing whether to add them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/olgaiv39/claude-oss-skills/dependency-review
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.

Any agent
npx skills add olgaiv39/claude-oss-skills --skill dependency-review
Clone the repo
git clone --depth 1 https://github.com/olgaiv39/claude-oss-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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/olgaiv39/claude-oss-skills/dependency-review/github.svg)](https://agentmods.dev/skills/olgaiv39/claude-oss-skills/dependency-review)
Your own site
<a href="https://agentmods.dev/skills/olgaiv39/claude-oss-skills/dependency-review"><img src="https://agentmods.dev/badge/skills/olgaiv39/claude-oss-skills/dependency-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/olgaiv39/claude-oss-skills/dependency-review"><img src="https://agentmods.dev/badge/skills/olgaiv39/claude-oss-skills/dependency-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,140 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 $0.00073 $0.01140
Opus 5 $0.00036 $0.00570
Sonnet 5 $0.00015 $0.00228
Haiku 4.5 $0.00007 $0.00114

Measured 12d ago against content hash 52b148d8c27e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dependency-review 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.

skills/dependency-review/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dependency-review

Decide whether to add a proposed dependency before it is added. Do not install anything or modify project files while using this skill.

Activate when

  • A new runtime or development dependency is proposed
  • An existing dependency upgrade would pull new transitive packages
  • A failing build suggests adding a package to resolve it

Do not activate when

  • The package is already a project dependency and no version changes
  • The task is a code change with no new dependency -> use implement-minimal
  • The task is a failing test unrelated to dependencies -> use test-and-debug

Required inputs

  • The exact package name and, if known, the version or range
  • The problem the dependency is meant to solve
  • Whether it is a runtime or development dependency

Low-resource policy

Read the first of these that exists, then follow it:

  • ${CLAUDE_PROJECT_DIR}/.claude/shared/LOW_RESOURCE.md
  • $HOME/.claude/shared/LOW_RESOURCE.md

If neither exists, apply this fallback: run one expensive command at a time, prefer the narrowest validation, disable watch mode, reuse existing environments, and run full validation only at a milestone boundary. Do not scan the whole filesystem to locate the policy.

Context-efficiency policy

Read the first of these that exists, then follow it:

  • ${CLAUDE_PROJECT_DIR}/.claude/shared/CONTEXT_EFFICIENCY.md
  • $HOME/.claude/shared/CONTEXT_EFFICIENCY.md

If neither exists, apply this fallback: select files before reading; use targeted searches and bounded ranges; do not preload references; do not reread unchanged files; finish one atomic increment and stop; create a compact handoff before context is exhausted.

Facts that must not be assumed

  • The package manager and lockfile in use
  • That the package is actively maintained
  • That the license is compatible with public release
  • The size of the transitive dependency tree

Preflight

  1. Identify the ecosystem and manifest -> references/ecosystem-review.md
  2. Read the existing manifest to see current dependencies and conventions
  3. Determine whether a current dependency or platform API already solves it

Read the full file on GitHub · 137 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 137 lines · 73 tokens per session scan A 52b148d8c27e

Subscribe to this mod's changes

dependency-review is a skill published in the GitHub repository olgaiv39/claude-oss-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,140 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

agentplane-task-closure-recovery

Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.

basilisk-labs/agentplane · 46 tokens

reviewing-code-quality

Reviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict. Use when a change risks oversized files, needless layers, feature logic leaking into shared code, or clever indirection. Do not use for a trivial obvious edit, or for a check that is only about whether…

FlyFission/nuclear-grade-context-engineering · 73 tokens

review-deep

Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.

ShreyPaharia/octomux · 52 tokens

review-orchestrator

Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.

ShreyPaharia/octomux · 41 tokens

audit

Use for PACEflow internal full audit: run five independent review agents, verify evidence from code/tests/logs, de-duplicate findings, and produce a severity-ranked report for release gates or comprehensive code review.

paceaitian/paceflow · 44 tokens

readonly-review

Run a no-network read-only review practice with two explorer steps and one synthesis step.

Ranvier-Technologies/pixir · 20 tokens