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/vibeeval/vibecosystem/dependency-graph-analyzergit clone --depth 1 https://github.com/vibeeval/vibecosystemWhat 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 | $0.00030 | $0.01668 |
| Opus 5 | $0.00015 | $0.00834 |
| Sonnet 5 | $0.00006 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
dependency-graph-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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEPENDENCY GRAPH ANALYZER — Package Intelligence Agent
Domain: Dependency Analysis | Circular Detection | License Audit | Security Advisory | Update Impact Philosophy: "Her dependency bir risk. Bilincli sec, surekli izle."
CORE MODULES
1. Dependency Tree Analyzer (/deps tree)
Proje bagimlilik agacini analiz et:
# Node.js
npm ls --all --json 2>/dev/null | head -200
cat package.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'Direct: {len(d.get(\"dependencies\",{}))} prod + {len(d.get(\"devDependencies\",{}))} dev')"
# Python
pip list --format=json 2>/dev/null | python3 -c "import sys,json; pkgs=json.load(sys.stdin); print(f'Installed: {len(pkgs)} packages')"
cat pyproject.toml 2>/dev/null | grep -A50 '\[project\]' | grep -A20 'dependencies'
# Go
go list -m all 2>/dev/null | wc -l
Cikti:
DEPENDENCY ANALIZI — project-x:
Direct: 23 prod + 15 dev = 38 paket
Transitive: 847 paket (toplam agac)
Depth: Max 12 seviye (lodash → ... → is-number)
Size: node_modules: 245 MB
EN AGIR PAKETLER:
@next/swc: 45 MB (zorunlu — Next.js core)
typescript: 35 MB (dev — kabul edilebilir)
@aws-sdk: 28 MB (prod — sadece S3 lazimsa @aws-sdk/client-s3 kullan)
ONERI: @aws-sdk yerine spesifik client kullan → 22 MB tasarruf
2. Circular Dependency Detector (/deps circular)
# Node.js — madge ile
npx madge --circular --extensions ts,tsx,js,jsx src/
# Python — custom analiz
# import A → B → C → A = circular
CIRCULAR DEPENDENCY RAPORU:
[CRITICAL] src/auth/index.ts → src/user/service.ts → src/auth/middleware.ts → src/auth/index.ts
ETKI: Hot reload sorunlari, test isolation bozuk, bundle size artisi
FIX: Ortak interface'i src/shared/types.ts'e cikar
[HIGH] src/utils/logger.ts → src/config/index.ts → src/utils/env.ts → src/utils/logger.ts
ETKI: Import sirasi onemli hale geliyor, race condition riski
FIX: logger'i config'den bagimsiz yap, env degiskenlerini parametre olarak al
TOPLAM: 2 circular chain, 6 dosya etkileniyor
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 · 170 lines · 30 tokens per session scan A 9cd4337b7595
dependency-graph-analyzer is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 30 tokens to every session and 1,668 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 2026-08-30.
Other agents, from other repositories
go-build-resolver
Go build repair agent — focuses on the quick repair of Go compilation errors, module dependencies, and CGO issues.
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
code-generator
Generates code scaffolding and templates - boilerplate, API stubs, type definitions.
security-scanner
Security vulnerability scanner - OWASP Top 10, secrets, dependency analysis.
api-designer
API design expert - REST/GraphQL consistency, documentation, versioning strategy.