Borrowing it
Nothing to install: this file belongs to sourjya/kiro-rails. 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/sourjya/kiro-rails/main/.claude/commands/review-dependency-risk.mdgit clone --depth 1 https://github.com/sourjya/kiro-railsWrote 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/commands/sourjya/kiro-rails/review-dependency-risk)<a href="https://agentmods.dev/commands/sourjya/kiro-rails/review-dependency-risk"><img src="https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-dependency-risk/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/commands/sourjya/kiro-rails/review-dependency-risk"><img src="https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-dependency-risk.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 | $0.00030 | $0.02695 |
| Opus 5 | $0.00015 | $0.01347 |
| Sonnet 5 | $0.00006 | $0.00539 |
| Haiku 4.5 | $0.00003 | $0.00269 |
Grade A, and why
review-dependency-risk scanned grade A with 1 finding 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
6. **Supply chain integrity beyond CVEs.** Typosquatting risk: package names that are one character off from popular libraries, or internal package names that could be claimed on public registries (dependency confusion). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before scanning, read docs/decisions/ ADRs if they exist. Use documented dependency decisions (accepted vendor lock-in, intentional SDK coupling) to distinguish intentional choices from accidental risk.
Act as a principal-level software engineer and supply chain security specialist performing a comprehensive dependency risk audit.
Your mission is not to list packages. It is to determine whether the project's dependency graph is lean, secure, legally compliant, and structurally sound - and whether the team could survive a critical dependency disappearing, being compromised, or changing license overnight. A dependency that works today but cannot be replaced, audited, or justified is a liability.
Activation Triggers
Run this review when:
- A Tier 3 (sprint-end) security review is scheduled
- A significant number of dependencies were added or upgraded in the sprint
- A dependency manifest (
package.json,pyproject.toml) has been substantially modified - A supply chain incident is reported in the ecosystem (e.g., compromised npm package)
- Before any major release or deployment to production
Review Objectives
Identify:
-
Dependency necessity and bloat. Packages that are unused, imported but never called, or trivially replaceable with standard library code. Dev dependencies leaked into production bundles or runtime manifests. Packages added speculatively during prototyping and never removed. For every dependency, answer: what breaks if this is removed?
-
Dependency amplification and transitive risk. The amplification factor of each direct dependency - how many transitive packages it pulls in. Phantom dependencies: packages used in code but not declared in the manifest, resolved only through transitive installation. Transitive dependencies that are unmaintained, deprecated, or have known vulnerabilities even when the direct dependency is healthy. Flag where a single direct dependency is responsible for more than 30% of the total transitive tree.
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 · 177 lines · 30 tokens per session scan A 83022c73f9a0
review-dependency-risk is a command published in the GitHub repository sourjya/kiro-rails (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 2,695 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.