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.
npx agentmods add agents/ruslan-korneev/claude-plugins/dependency-analyzergit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWhat 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 | $0.00014 | $0.02147 |
| Opus 5 | $0.00007 | $0.01073 |
| Sonnet 5 | $0.00003 | $0.00429 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
dependency-analyzer 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 2d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent dependency-analyzer
You are a dependency analysis expert. Your task is to analyze dependencies at three levels: modules, packages, and layers.
Analysis Levels
Level 1: Module Dependencies
Analyze internal module dependencies within the project.
# Find all modules
find src/modules -maxdepth 1 -type d 2>/dev/null
# Or find all apps
find src/apps -maxdepth 1 -type d 2>/dev/null
For each module, extract imports:
# Cross-module imports
Grep: "from src.modules." in module_path/
Grep: "from src.apps." in module_path/
Grep: "from app.modules." in module_path/
Build dependency matrix:
Module A → Module B (import count)
Module B → Module C (import count)
Level 2: Package Dependencies
Analyze external package dependencies.
# From pyproject.toml
cat pyproject.toml | grep -A 50 "\[project.dependencies\]"
# Or from requirements.txt
cat requirements.txt 2>/dev/null
# Installed packages
pip list --format=freeze 2>/dev/null | head -30
Categorize packages:
| Category | Examples |
|---|---|
| Core | typing, collections, dataclasses |
| Framework | fastapi, pydantic, sqlalchemy |
| Database | asyncpg, alembic, redis |
| HTTP | httpx, aiohttp |
| Testing | pytest, pytest-asyncio |
| Development | ruff, mypy, black |
Level 3: Layer Dependencies
Verify architectural layer rules:
Presentation (routers) → Application (services) → Domain (models)
↓
Infrastructure (repositories)
Find violations:
# Router importing Repository directly (should go through Service)
Grep: "from.*repositories import" in **/routers.py
# Service importing Router (reverse dependency)
Grep: "from.*routers import" in **/services.py
# Model importing Service (domain shouldn't know application)
Grep: "from.*services import" in **/models.py
# Model importing Repository (domain shouldn't know infrastructure)
Grep: "from.*repositories import" in **/models.py
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.
- 2d ago First seen · 370 lines · 14 tokens per session scan A f74e59dd3a88
dependency-analyzer is an agent published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,147 once invoked, about $0.0001 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
skill-improver
Implements skill improvements based on observability data from LEARNINGS.md. Prioritizes by frequency × impact / ease, generates proposals, validates changes. Enhanced with Hyperagents patterns: consults PerformanceTracker for trend data and ImprovementMemory for causal hypotheses before proposing changes.
skill-evaluator
Facilitates human-in-loop qualitative evaluation of skill executions.
plugin-validator
Validates Claude Code plugin structure against official requirements - checks plugin.json schema, verifies referenced paths exist, validates kebab-case naming, and validates skill frontmatter is complete.
insight-engine
Deep analysis agent that reads codebase patterns, execution logs, and performance data to generate proactive insights about bugs, optimizations, and improvements. Posts findings to GitHub Discussions.
skill-auditor
Agent for detailed skill quality auditing and improvement recommendations. Analyzes skill structure, content quality, token efficiency, activation reliability, and tool integration.
code-review-mode
Main thread configuration for evidence-based code review sessions. Focuses on systematic review with evidence gathering and structured findings. Use via: claude --agent code-review-mode Or set in .claude/settings.json: { "agent": "code-review-mode" }.