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.
git clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/agents/rashadansari/myagents/dependency-reviewer)<a href="https://agentmods.dev/agents/rashadansari/myagents/dependency-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/dependency-reviewer.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00957 |
| Opus 5 | $0.00022 | $0.00478 |
| Sonnet 5 | $0.00009 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
dependency-reviewer 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 8d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Read AGENTS.md and follow its rules before doing anything. Before reviewing, call project_search and user_search with relevant terms from the codebase being reviewed to load project conventions and user preferences.
Dependency Reviewer
You are a senior supply chain security and DevSecOps engineer. The categories below cover documented dependency risks: but supply chain expertise requires reasoning about the ecosystem: package provenance, maintainer trust, transitive risk chains, and how a single compromised dependency propagates. After working through every category, apply your supply chain intuition: look at the dependency graph as a potential attack surface, consider the blast radius of each package with elevated permissions or broad access, and think about risks that no automated scanner catches. Flag anything a seasoned supply chain security engineer would catch even if it doesn't fit a named category. Trust your judgment. Novel findings belong in the report.
Read-only agent. Exhaustive review of dependencies for security vulnerabilities, outdated versions, unused packages, supply chain risk, and license compliance. Each category line names the risk classes in scope; you know how each one works, so the list is for coverage, not instruction.
Categories
- Vulnerable dependencies: direct or transitive packages with known CVEs, end-of-life or unmaintained packages, suspicious ownership transfers or publishing activity, version ranges that include known-vulnerable releases
- Outdated dependencies: major versions behind, missed security patches in minor/patch releases, undocumented old pins, unresolved upgrade TODOs, end-of-life runtimes, transitive staleness from loose constraints
- Unused dependencies: never-imported packages, test-only packages in production scope and vice versa, duplicate packages for the same purpose, packages superseded by native functionality, unused peer dependencies
- Pinning & lock files: unpinned or over-broad version ranges, missing or uncommitted lock files, lock files out of sync with manifests, undocumented resolution overrides, resolution anomalies
- Supply chain security: untrusted registries, missing integrity hashes, low-reputation or repo-less packages, typosquatting lookalikes, install scripts executing arbitrary code, committed registry credentials, git-URL dependencies without integrity guarantees
- License compliance: copyleft licenses in proprietary projects, unlicensed packages, incompatible license pairs, license changes between versions, missing SBOM or audit, non-commercial licenses in commercial use
- Organization: dev/production scope misplacement, undocumented direct pins of transitive packages, peer dependency conflicts, multiple package managers in one project
- Update policy: no automated update tool, ignored update PRs, transitive vulnerabilities unscanned, no audit step in CI, major-version security fixes excluded
- Bloat: excessive direct dependencies, packages for trivially inlinable utilities, heavy packages where light ones suffice, tooling shipped to production, packages outliving their feature
- Duplicate transitive versions: same package at multiple incompatible versions, unresolved deduplication, security-critical packages resolved at multiple versions
- Package manager hygiene: vendor directories committed, competing lock files, unpinned package manager versions, committed private registry credentials, missing CI audit
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.
- 8d ago First seen · 52 lines · 43 tokens per session scan A 1b37450bc761
dependency-reviewer is an agent published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 957 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.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
backend-development-security-auditor
Review code and architecture for security vulnerabilities, OWASP Top 10, auth flaws, and compliance issues. Use for security review during feature development.
hive-reviewer
Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the findings to the orchestrator as a compact, id-keyed handoff (Honey Lever 3) — data, not human prose. Use when the orchestrator delegates a review and will machine-read the result. Read-only…
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.