Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/neo4j-contrib/neo4j-skillsnpx agentmods add commands/neo4j-contrib/neo4j-skills/skill-refreshWrote 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/commands/neo4j-contrib/neo4j-skills/skill-refresh)<a href="https://agentmods.dev/commands/neo4j-contrib/neo4j-skills/skill-refresh"><img src="https://agentmods.dev/badge/commands/neo4j-contrib/neo4j-skills/skill-refresh/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/commands/neo4j-contrib/neo4j-skills/skill-refresh"><img src="https://agentmods.dev/badge/commands/neo4j-contrib/neo4j-skills/skill-refresh.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 | $0.00000 | $0.02069 |
| Opus 5 | $0.00000 | $0.01035 |
| Sonnet 5 | $0.00000 | $0.00414 |
| Haiku 4.5 | $0.00000 | $0.00207 |
Grade A, and why
skill-refresh 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 4d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neo4j Skills Refresh
You are running inside a headless Claude Code session in the neo4j-skills repository.
Goal: scan Neo4j release notes and deprecation pages, then update any SKILL.md and references/ files that are stale, outdated, or missing new features. Open no PRs or commits — output only file edits. The workflow will handle git and PR creation.
Step 1 — Fetch release signals
Fetch and read each source. Extract: new syntax, deprecated APIs, removed features, version bumps, new config options, new tools/libraries. Note the source URL and Neo4j (or GDS) version for each finding.
Release notes / changelogs:
- https://neo4j.com/release-notes/ — scan releases published in the last 30 days
- https://github.com/neo4j/neo4j/wiki/Neo4j-2026-changelog
- https://github.com/neo4j/neo4j/wiki/Changelog — scan entries from the last 30 days
- https://github.com/neo4j/graph-data-science/releases - scan entries from the last 30 days
- https://github.com/neo4j/graph-data-science-client/releases - scan entries from the last 30 days
Deprecation and removal pages:
- https://neo4j.com/docs/cypher-manual/current/deprecations-additions-removals-compatibility/
- https://neo4j.com/docs/operations-manual/current/deprecations/
- https://neo4j.com/docs/graphql/current/deprecations/
For each finding, note:
- What changed (new / deprecated / removed / renamed)
- Which Neo4j (or GDS) version introduced it
- Which skill(s) it likely affects
Step 2 — Map findings to skills
Discover skills dynamically:
ls -d neo4j-*-skill/
For each affected skill, read its SKILL.md and any linked references/ files before making changes.
Step 3 — Fetch supporting docs
For each finding that affects a skill, fetch the relevant section of the actual Neo4j docs to get precise new syntax, parameter names, and examples before editing. Do not guess API shape from release note summaries alone.
Doc roots:
- Cypher manual: https://neo4j.com/docs/cypher-manual/current/
- Operations manual: https://neo4j.com/docs/operations-manual/current/
- Python driver: https://neo4j.com/docs/python-manual/current/
- JavaScript driver: https://neo4j.com/docs/javascript-manual/current/
- Java driver: https://neo4j.com/docs/java-manual/current/
- Go driver: https://neo4j.com/docs/go-manual/current/
- .NET driver: https://neo4j.com/docs/dotnet-manual/current/
- GDS: https://neo4j.com/docs/graph-data-science/current/
- GDS Python client: https://neo4j.com/docs/graph-data-science-client/current/
- GraphQL: https://neo4j.com/docs/graphql/current/
- Aura: https://neo4j.com/docs/aura/current/
- Kafka connector: https://neo4j.com/docs/kafka/current/
- Spark connector: https://neo4j.com/docs/spark/current/
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.
- 4d ago First seen · 160 lines · 0 tokens per session scan A 421522f4a86b
skill-refresh is a command published in the GitHub repository neo4j-contrib/neo4j-skills (109 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,069 tokens. 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 2026-09-07.
Other commands, from other repositories
init
Initialize configurations for Supabase local development.
setup_research_plan
Set up or start a research project.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.
1-plan
Plans a thread and generates thread-specific spec documents.
4-finalize
Finalizes a reviewed thread, updates project documentation, and handles cleanup.
arckit.data-model
Create comprehensive data model with entity relationships, GDPR compliance, and data governance.