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 | $0.02495 |
| Opus 5.5 | $0.00000 | $0.00998 |
| Sonnet 5.5 | $0.00000 | $0.00499 |
| Haiku 4.5 | $0.00000 | $0.00249 |
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 26d 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 — 172 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.
Working tree already includes any open, unmerged PRs from prior skill-refresh runs that the workflow could merge cleanly (listed below, after the ---, with any it could not merge due to conflicts). Unrelated open PRs are never merged in — only prior skill-refresh automation PRs. Treat that merged state as your baseline, not origin/main:
- Don't re-propose changes those PRs already made — read the current file content, not what you might remember main looking like.
- Compute every
version:bump from the version currently in the file (which already reflects any merged PR's bump), so you never re-use or skip a version number a merged PR already claimed. - If a listed PR was skipped for conflicts, don't try to guess and duplicate its likely changes — just proceed with your own scan and note it exists in the summary.
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
- https://github.com/neo4j/neo4j-graphrag-python/releases - scan entries from the last 30 days (CHANGELOG: https://github.com/neo4j/neo4j-graphrag-python/blob/main/CHANGELOG.md)
- https://registry.npmjs.org/@neo4j-nvl/base - Neo4j Visualization Library (@neo4j-nvl/*):
dist-tags+ newestversionsentries (no GitHub releases feed; source repo not public)
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.
- 26d ago Changed · +4 lines 60663bb843c6
- 1mo ago Changed · +8 lines 0a78b6f1bbe4
- 1mo 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 (116 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,495 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.
session-list
List recent sessions from the project ledger and offer to view one.
session-stop
Stop recording and save this agent session to the project ledger.
session-start
Start recording this agent session to the project ledger.
status
Check SageOx project status including authentication, sync, and daemon health.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.