The list is all eleven.
Read tools need read scopes, and the write tools are listed because this key can call them.
OSS and Cloud
Skene OSS and Cloud. Choose where you work.
A CLI run ends with a journey file. Skene Cloud keeps a workspace around it and reviews the next change you ship. Start in Cloud, or push your CLI journey across. The canvas, launch checks and hosted MCP server work from that shared record.
Sign in, create a workspace, connect a source. The free tier is one audit, no card.
skene-ai[bot]
Changes requested
Missing tracking
This PR has 1 tracking issue (1 missing). See inline comments.
Medium
[event redacted] missing at [file redacted]:89
CLI · Cloud
Two products, and what each one does on its own.
A journey.yaml you push from the CLI outranks the Analyze pipeline: a hand-maintained journey always wins.
Scroll to compare both products.
| Capability | Skene CLI (OSS) | Skene Cloud |
|---|---|---|
| Journey from code and schema | Seven stages | Five stages by default |
| PostgreSQL connector, credentials never stored | ✓ --db-url | ✓ Supabase OAuth, read-only by default |
| Runs on your machine, your model provider, MIT | ✓ | Managed |
| Review on every change you ship, one-click fixes, /skene fix | – | ✓ |
| Journey canvas, editable, agent-assisted | – | ✓ |
| Launch checks: plan, verify, launch ready, check | – | ✓ |
| Events table with statuses and ignore rules | – | ✓ |
| Flows: one script tag, real user paths, 90-day retention | – | ✓ |
| Hosted MCP server, 11 tools for coding agents | – | ✓ |
| Record kept between runs | – | ✓ |
The release check, in your review flow.
Skene reviews every pull request on the repository you link for removed or broken tracking. It requests changes with inline comments on the exact lines, or passes.
- One-line fixes arrive as committable GitHub suggestions
- Anything larger arrives as a “Prompt to fix this” block, pasteable into a coding agent
/skene fixopens a follow-up PR restoring what the diff deleted, and only that- When a later run passes, Skene dismisses its own earlier change requests
skene-ai[bot]
Later review
No tracking issues detected.
Skene analytics drift check passed. No tracking issues detected.
Earlier request dismissed
Tracking issue fixed; superseded by later Skene pass review.
The workspace: canvas, events, Flows.
The journey lives on an editable canvas. Describe a change in plain language and the agent updates the saved journey. Inspect its milestones and evidence on the canvas. Measurement plans start from the outcome you want to test, without asking you to invent event names.
- Verify compares required events against your code and arriving evidence: ready or missing
- Check computes the metric after launch: current, previous, change, goal met or not
- Flows maps real user paths from one dependency-free script tag, purged after 90 days
before
Activation
saved
Activation
setup_completed
For your agent: 11 tools over MCP.
The hosted MCP server authenticates with a workspace API key. Read tools need read scopes; in read-only mode write tools are filtered out of the list entirely. The deterministic gate is callable over HTTP or as an MCP tool, and it can disagree with the model review by design.
- Two key types: a server-side secret key, and a write-only publishable key safe to embed
- Exactly two roles, owner and member. No permission matrix to configure
The write tools are not in it.
They are filtered out of the list entirely, so the agent is never offered a tool it would be refused.
Start with the free audit.
One audit per workspace, once. No card.