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 skills/jansenanalytics/claudex/knowledge-graphnpx skills add JansenAnalytics/claudex --skill knowledge-graphgit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/knowledge-graph)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/knowledge-graph"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/knowledge-graph.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01710 |
| Opus 5 | $0.00023 | $0.00855 |
| Sonnet 5 | $0.00009 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
knowledge-graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Graph Skill
Overview
SQLite-backed entity-relationship store. Entities (people, projects, decisions, tools, rules) connected by typed relations (decided-by, depends-on, supersedes, etc.). Full-text search, path finding, timeline, and auto-ingestion from markdown files.
Why this over flat files: "Which database did we choose for web-platform, who decided it, and what did it supersede?" → one query returns the decision, who made it, when, what it superseded, and what it relates to. With flat files, that's 5 greps across MEMORY.md and daily logs.
Script
KG=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/knowledge-graph/scripts/kg.cjs
node $KG <command> [args]
Entity Types
| Type | Emoji | Use For |
|---|---|---|
person |
👤 | People (the tech lead, a teammate) |
project |
📁 | Projects (web-platform, mobile-app) |
decision |
⚖️ | Design decisions, choices made |
tool |
🔧 | Tools, services, libraries |
account |
💰 | API accounts, service accounts, credentials |
concept |
💡 | Ideas, concepts, mental models |
rule |
📏 | Rules, constraints, invariants |
event |
📅 | Events, meetings, incidents |
skill |
🎯 | OpenClaw skills |
file |
📄 | Important files, configs |
service |
⚙️ | Running services, Docker containers |
Relation Types
| Relation | Meaning | Auto-behavior |
|---|---|---|
decided-by |
Who made this decision | — |
depends-on |
X requires Y | — |
related-to |
Loosely connected | — |
supersedes |
X replaces Y | Auto-marks Y as superseded 🔴 |
belongs-to |
X is part of project Y | — |
created-by |
Who/what created this | — |
blocked-by |
X is blocked by Y | — |
implements |
Tool X implements decision Y | — |
uses |
X uses tool/library Y | — |
contradicts |
X conflicts with Y | — |
derived-from |
X was derived from Y | — |
part-of |
X is a component of Y | — |
triggers |
X triggers Y | — |
configures |
X configures Y | — |
owns |
X owns/manages Y | — |
What ships with it
1 file 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.
- 2d ago First seen · 198 lines · 47 tokens per session scan A e184550ef6b0
knowledge-graph is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,710 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 2026-09-03.
Other skills, from other repositories
memory-manager
Persistent project memory using SQLite + FTS5 + BM25. Fast, zero dependencies (stdlib only), production-ready. Progressive disclosure with 3 layers (compact/index/detailed).
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.