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/memgraph/ai-toolkit/agent-context-graphnpx skills add memgraph/ai-toolkit --skill agent-context-graphgit clone --depth 1 https://github.com/memgraph/ai-toolkitWhat 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 | $0.00012 | $0.00616 |
| Opus 5 | $0.00006 | $0.00308 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
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.
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"
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 · 75 lines · 12 tokens per session scan A d4ef11495b65
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
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.
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.