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 skills add vibeeval/vibecosystem --skill code-knowledge-graphgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/skills/vibeeval/vibecosystem/code-knowledge-graph)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/code-knowledge-graph"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/code-knowledge-graph/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/skills/vibeeval/vibecosystem/code-knowledge-graph"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/code-knowledge-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.03262 |
| Opus 5.5 | $0.00010 | $0.01305 |
| Sonnet 5.5 | $0.00005 | $0.00652 |
| Haiku 4.5 | $0.00002 | $0.00326 |
Grade A, and why
code-knowledge-graph 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 1mo 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Knowledge Graph - Codebase Graph Analysis
Codebase'i knowledge graph olarak modeller. Dosya, modul, fonksiyon ve class'lar node; import, call, inheritance ve composition iliskileri edge olur. Sonuc: Mermaid diagram + JSON graph data.
Neden Knowledge Graph?
Kod text degil, graph'tir. Her dosya diger dosyalara baglidir. Bu baglantilari anlamadan:
- Refactoring yaparken neyi kiracagini bilemezsin
- Dead code'u guvenle silemezsin
- Yeni feature'in nereye oturacagini gormezsin
- Circular dependency'lerin kokunu bulamazsin
Knowledge graph tum bu iliskileri gorsellestirir ve olculebilir yapar.
Kullanim
/code-knowledge-graph [hedef-dizin] [--focus module] [--depth N] [--format mermaid|json|both]
Ornekler
# Tum codebase analizi
/code-knowledge-graph src/
# Belirli module odaklan
/code-knowledge-graph src/ --focus auth
# Sadece circular dependency kontrolu
/code-knowledge-graph src/ --focus circular
# Hotspot analizi
/code-knowledge-graph src/ --focus hotspots
# Orphan/dead code tespiti
/code-knowledge-graph src/ --focus orphans
Graph Olusturma Adimlari
Adim 1: Node Discovery
# Dosya agaci
tldr tree ${PATH:-src/} --ext .py
# Kod yapisi: fonksiyonlar, class'lar, export'lar
tldr structure ${PATH:-src/} --lang python
Her dosya, class, fonksiyon ve export bir node olur.
Adim 2: Edge Extraction
# Dosyanin import'lari (outgoing edges)
tldr imports ${FILE}
# Modulu kim import ediyor? (incoming edges)
tldr importers ${MODULE} ${PATH:-src/}
# Cross-file call graph
tldr calls ${PATH:-src/}
Her import ve fonksiyon cagrisi bir directed edge olur.
Adim 3: Layer Detection
# Architectural layer analizi
tldr arch ${PATH:-src/}
Node'lar 3 katmana ayrilir:
| Katman | Tanim | Ornekler |
|---|---|---|
| Entry | Disaridan cagirilan, ici cagirmayan | routes, cli, main, handlers |
| Middle | Hem cagrilan hem cagirir | services, business logic |
| Leaf | Cagirilan ama baskasini cagirmayan | utils, helpers, constants |
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.
- 1mo ago First seen · 400 lines · 24 tokens per session scan A 8f32a7c0c9f4
code-knowledge-graph is a skill published in the GitHub repository vibeeval/vibecosystem (540 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 3,262 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
architecture-review
Analyze Python module architecture using pyscn - class coupling (CBO), cohesion (LCOM), dependency cycles, and module communities. Use when user asks about architecture, module structure, coupling, circular dependencies, or which files to review or change together.
refactoring
Find refactoring targets in Python code using pyscn - duplicate code (clones), overly complex functions, and dead code. Use when user asks about refactoring, code duplication, complexity hotspots, unreachable code, or cleaning up a codebase.
enola
Use Enola when investigating architecture, dependencies, blast radius, cross-repository relationships, structural regressions, or what a code change did to the system.
windows-compat
Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…
cortex-memory
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.