agent-context-graph

A setup and diagnostic guide for capturing Claude Code activity in Memgraph, a graph database. It connects runtime events through hooks and connectors.

In plain words
What is it for?
Use it to bootstrap the connection, check the Claude Code runtime and connectors, and run a basic hook test.
Why use it?
It helps find out whether activity is being recorded and why graph facts may be missing, including whether Memgraph is reachable.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/memgraph/ai-toolkit/agent-context-graph
Any agent
npx skills add memgraph/ai-toolkit --skill agent-context-graph
Clone the repo
git clone --depth 1 https://github.com/memgraph/ai-toolkit

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00616
Opus 5 $0.00006 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 2d ago against content hash d4ef11495b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-context-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.

context-graph/plugins/agent-context-graph-claude/skills/agent-context-graph/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Context Graph

Use this skill when the user asks whether Claude Code activity is being captured, how Agent Context Graph hooks work, or why graph facts are missing.

Model

Claude Code Plugin -> Claude Code Runtime Adapter -> Event Protocol -> Graph Connector -> Memgraph.

The plugin only installs runtime hook wiring. It must not assign graph meaning. Graph connectors decide which normalized events matter.

Checks

For first-time setup, run the plugin bootstrap once. It delegates to the CLI bootstrap and falls back to uvx if agent-context-graph is not installed yet:

./scripts/bootstrap.sh

If bootstrap says Memgraph is not reachable, tell the user to start Memgraph:

docker run --rm -p 7687:7687 memgraph/memgraph

Run the single CLI doctor first. It checks the same Python environment that the hook command uses:

agent-context-graph doctor --runtime claude-code --connector skills-graph --connector actions-graph --connector sessions-graph

If doctor is not available, use the strict hook smoke:

printf '{"hook_event_name":"Stop","session_id":"doctor"}' \
  | agent-context-graph hook run claude-code --connector skills-graph --connector actions-graph --connector sessions-graph --strict

Do not check skills_graph with system python3; agent-context-graph may be installed in an isolated uv tool or pipx environment.

Configuration

Connection settings live in ~/.config/context-graph/config.toml. Hook subprocesses read from this file (not environment variables).

If MEMGRAPH_URL, MEMGRAPH_USER, MEMGRAPH_PASSWORD, or MEMGRAPH_DATABASE environment variables are set when bootstrap runs, they are automatically written to the config file. No manual config set needed in that case.

View current config:

agent-context-graph config show

Set values:

agent-context-graph config set identity.user_id "username"
agent-context-graph config set memgraph.url "neo4j://coordinator:7687"
agent-context-graph config set memgraph.user "username"
agent-context-graph config set memgraph.password
agent-context-graph config set memgraph.database "dbname"

Read the full file on GitHub · 75 lines

Changes

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.

  1. 2d ago First seen · 75 lines · 12 tokens per session scan A d4ef11495b65

Subscribe to this mod's changes

agent-context-graph is a skill published in the GitHub repository memgraph/ai-toolkit (112 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 616 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens