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 manhvann/codexkit --skill gkggit clone --depth 1 https://github.com/manhvann/codexkitWrote 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/manhvann/codexkit/gkg)<a href="https://agentmods.dev/skills/manhvann/codexkit/gkg"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/gkg/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/manhvann/codexkit/gkg"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/gkg.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00623 |
| Opus 5.5 | $0.00018 | $0.00249 |
| Sonnet 5.5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade C, and why
ck:gkg scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://gitlab.com/gitlab-org/rust/knowledge-graph/-/raw/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://gitlab.com/gitlab-org/rust/knowledge-graph/-/raw/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab Knowledge Graph (GKG)
Semantic code analysis engine using AST parsing and KuzuDB graph database. Enables IDE-like code navigation for AI assistants.
Status: Public beta | Requires: Git repository | Storage: ~/.gkg/
When to Use
- Find all usages of a function/class across codebase
- Go-to-definition for symbols
- Impact analysis before refactoring
- Generate architecture diagrams
- RAG-enhanced code understanding
Use repomix instead for: quick context dumps, any-language support, remote repos, token counting.
Quick Start
# Check installation
gkg --version
# Index current repo
gkg index
# Start server (for API/MCP)
gkg server start
# Stop before re-indexing
gkg server stop
Installation
# macOS/Linux
curl -fsSL https://gitlab.com/gitlab-org/rust/knowledge-graph/-/raw/main/install.sh | bash
# Windows (PowerShell)
irm https://gitlab.com/gitlab-org/rust/knowledge-graph/-/raw/main/install.ps1 | iex
Core Workflows
Index and Query
gkg index /path/to/project --stats
gkg server start
# Query via HTTP API at http://localhost:27495
Find Symbol Usages
- Index project:
gkg index - Start server:
gkg server start - Use MCP tool
get_referencesor HTTP API/api/graph/search
Impact Analysis
- Index affected repos
- Query
get_referencesfor changed symbols - Review all call sites before refactoring
Language Support
| Language | Cross-file Refs |
|---|---|
| Ruby | ✅ Full |
| Java | ✅ Full |
| Kotlin | ✅ Full |
| Python | 🚧 In progress |
| TypeScript | 🚧 In progress |
| JavaScript | 🚧 In progress |
References
- CLI Commands -
gkg index,gkg server,gkg remove,gkg clean - MCP Tools - 7 tools for AI integration
- HTTP API - REST endpoints for querying
- Language Details - Supported features per language
Key Constraints
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 92 lines · 44 tokens per session scan C be272e2c9d70
ck:gkg is a skill published in the GitHub repository manhvann/codexkit (89 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 623 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…