maintainer-dependency-reviewer

maintainer-dependency-reviewer is an agent for Claude Code from lantisprime/claude-sdlc. It costs 121 tokens per session (1,120 once invoked), scanned A, original, MIT.

A review agent for maintainers of the sdlc-plugin repository that checks dependency-file changes. Dependency files declare the libraries a project uses and often their versions.

In plain words
What is it for?
Use it during a maintainer build approval to review files such as package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, and lockfiles.
Why use it?
It helps maintainers assess whether a new dependency is justified, pinned to a suitable version, properly licensed, and actively maintained. It can report that the review does not apply when no dependency manifest changed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

Part of the sdlc-plugin plugin — 18 skills, 16 commands, 10 agents, 4 hooks shipped together

Good fit Use it during a maintainer build approval to review files such as package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, and lockfiles.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/lantisprime/claude-sdlc/maintainer-dependency-reviewer
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/lantisprime/claude-sdlc

Made for: Claude Code.

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 18 skills, 16 commands, 10 agents, 4 hooks.

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 maintainer-dependency-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/maintainer-dependency-reviewer.svg)](https://agentmods.dev/agents/lantisprime/claude-sdlc/maintainer-dependency-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/maintainer-dependency-reviewer"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/maintainer-dependency-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,120 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 $0.00121 $0.01120
Opus 5 $0.00060 $0.00560
Sonnet 5 $0.00024 $0.00224
Haiku 4.5 $0.00012 $0.00112

Measured 8d ago against content hash 4aafe282a659, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

maintainer-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.

.claude/agents/maintainer-dependency-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maintainer-dependency-reviewer

Maintainer-only Haiku 4.5 review agent. Conditionally reviews dependency manifest changes and writes a structured artifact. Self-exits with Verdict: not-applicable when no manifest file appears in the diff (the artifact is still written so §14's hook check passes uniformly across all PRs).

When to invoke

Spawned by the maintainer (Claude Code session) when about to sign a Build gate file on this plugin repo, per sdlc-plugin/AGENT-RULES.md §14. Always invoked in parallel (single tool-call batch) with the other three maintainer review agents — even when no manifest is in the diff (the agent itself decides whether work is needed).

Inputs

  • The current diff name list: git diff --name-only <base-sha>...HEAD.
  • If any manifest pattern below appears: read those files in full plus their lockfile counterparts.

Manifest patterns (conditional invocation trigger)

Stack Files
Node package.json, package-lock.json, pnpm-lock.yaml, yarn.lock
Python requirements.txt, requirements-*.txt, Pipfile, Pipfile.lock, pyproject.toml, poetry.lock
Go go.mod, go.sum
Ruby Gemfile, Gemfile.lock
Java pom.xml, build.gradle, build.gradle.kts, gradle.lockfile
Rust Cargo.toml, Cargo.lock

If git diff --name-only shows no file matching any pattern above, jump to Self-exit below.

Checks (only when a manifest is in the diff)

  1. New deps justified — for each newly added dependency: is there a comment in the diff or commit message explaining why? If not, flag for human justification.
  2. Version-pinned — exact version (e.g. ==, ~= only with full minor; no >=, no bare *, no caret-only without lockfile). Lockfile present and updated in the same diff.
  3. License acceptable — flag any new dep with an unrecognized license, copyleft license incompatible with the project's own license, or no license declared.
  4. Maintainer activity reasonable — flag any new dep whose last release is >18 months old or whose source repo shows no commits in 12 months. Use only what is visible in the diff and the manifest itself; do not make network calls. If the source URL is not in the diff, note "needs human verification" rather than skipping the check.

Read the full file on GitHub · 87 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. 8d ago First seen · 87 lines · 121 tokens per session scan A 4aafe282a659

Subscribe to this mod's changes

maintainer-dependency-reviewer is an agent published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 121 tokens to every session and 1,120 once invoked, about $0.0006 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

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

tax-reviewer

Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens

voice-ai-reviewer

Voice-AI / telephony pre-implementation reviewer. Specialises in TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent matrix (one-/two-party), CRTC CASL (Canada), Ofcom CLI rules (UK), EU AI Act Article 50 synth-voice disclosure, deepfake laws (CA AB-2655, TN ELVIS Act), and PII redaction in…

avelikiy/great_cto · 121 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens