Daily reports › 2026-10-27 · Is your tool safe to install today?
Daily install report: 2026-10-27
On 2026-10-27 we ran the real install of 423 agent add-ons across Claude Code, Codex, Grok Build, Cursor and Pi in a clean sandbox: 806 of 900 installs passed, 94 failed (12 of those only need an API key). Compared with the previous run (2026-10-26, 802/902): 0 confirmed broke, 0 really fixed, 15 flaky.
Get the weekly scorecard by email
Daily reports live on the site only, we never email them. The free weekly email (Tuesdays) has the week's install scorecard plus new tools.
Loading the signup form… or subscribe on Beehiiv
Form not loading? Subscribe on Beehiiv →
Tonight's verdicts by agent
| Agent | Installs | Passed | Needs an API key | Broken (2+ nights) | Pending re-check | Flaky |
|---|---|---|---|---|---|---|
| Claude Code | 367 | 340 | 6 | 21 | 0 | 0 |
| Codex | 65 | 65 | 0 | 0 | 0 | 0 |
| Grok Build | 330 | 316 | 0 | 13 | 1 | 13 |
| Cursor | 52 | 29 | 6 | 17 | 0 | 2 |
| Pi | 86 | 56 | 0 | 30 | 0 | 0 |
How to read this: Needs an API key means the add-on asked for a key or token our keyless sandbox doesn't have, so it's probably fine on your machine once you add yours. Pending failed tonight (after a retry) but worked last night; we only call it broken if it fails again tomorrow. Flaky flip-flopped lately or only passed on retry.
Standout pick
Superpowers: installed cleanly in 4 agents (Claude Code, Codex, Grok Build, Pi), 314k GitHub stars. Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, it teaches Claude how to author and test new ski
How we pick: clean in every agent we tested it in, nothing flaky or pending, new and really-fixed add-ons first, then GitHub stars. Never sponsored.
Confirmed broke (0)
Nothing newly confirmed broken (failing two nights in a row after a good night).
Really fixed (0)
Nothing came back after failing two or more nights.
Pending re-check (1)
Failed tonight, worked last night. Not calling these broken yet.
- Oracledb in Grok Build
Flaky (15)
These flip-flopped between pass and fail recently. They pass tonight, but give them a retry if one hiccups on you.
- @putervision/vision-memory-mcp in Cursor
- Alloydb Omni in Grok Build
- Bigdata Com in Grok Build
- Expo in Grok Build
- Looker in Grok Build
- MCP git (reference) in Cursor
- Mergify in Grok Build
- Migration To AWS in Grok Build
- Neon in Grok Build
- Quo in Grok Build
- Railway in Grok Build
- Slack in Grok Build
- Snowflake Cortex Code in Grok Build
- SonarQube in Grok Build
- Zscaler in Grok Build
Needs your API key (12)
Not broken, just shy without credentials. Our sandbox has no keys on purpose.
- @currents/mcp in Claude Code
- @currents/mcp in Cursor
- @postman/postman-mcp-server in Claude Code
- @postman/postman-mcp-server in Cursor
- @respira/wordpress-mcp-server in Claude Code
- @respira/wordpress-mcp-server in Cursor
- @taazkareem/clickup-mcp-server in Claude Code
- @taazkareem/clickup-mcp-server in Cursor
- @zereight/mcp-gitlab in Claude Code
- @zereight/mcp-gitlab in Cursor
- obsidian-mcp-server in Claude Code
- obsidian-mcp-server in Cursor
Dropped from the lists (1)
- bruin
Everything failing 2+ nights (81)
- @dallay/agentsync in Claude Code
- @dallay/agentsync in Cursor
- @haven_ai/mcp in Claude Code
- @haven_ai/mcp in Cursor
- @imgly/codesign-mcp in Claude Code
- @imgly/codesign-mcp in Cursor
- @ironbee-ai/devtools in Claude Code
- @ironbee-ai/devtools in Cursor
- @microsoft/workiq in Claude Code
- @microsoft/workiq in Cursor
- @yawlabs/ctxlint in Claude Code
- @yawlabs/ctxlint in Cursor
- agent-device in Claude Code
- agent-device in Cursor
- Amazon Location Service in Pi
- Amplitude in Pi
- apple-notes-mcp in Claude Code
- apple-notes-mcp in Cursor
- Atomic Agents in Pi
- AWS Amplify in Pi
- AWS Serverless in Pi
- AWS Transform in Pi
- blitzstrike in Claude Code
- blitzstrike in Cursor
- Chrome DevTools in Pi
- Chrome DevTools MCP in Pi
- Circleback in Pi
- Clangd LSP in Grok Build
- Cloud SQL Mysql in Pi
- Cloud SQL Sqlserver in Pi
- Code Modernization in Claude Code
- Csharp LSP in Grok Build
- Databases On AWS in Pi
- Dataproc in Pi
- Dataverse in Pi
- Deploy On AWS in Pi
- dsh-mcp-connector in Claude Code
- dsh-mcp-connector in Cursor
- ffmpeg-skill in Claude Code
- ffmpeg-skill in Cursor
- Firestore Native in Pi
- gdharness in Claude Code
- gdharness in Cursor
- Gopls LSP in Grok Build
- Jdtls LSP in Grok Build
- Knowledge Catalog in Pi
- kordoc in Claude Code
- kordoc in Cursor
- Kotlin LSP in Grok Build
- Learn With Coursera in Grok Build
- lerianstudio-matcher-mcp in Claude Code
- lerianstudio-matcher-mcp in Cursor
- Looker in Pi
- Lua LSP in Grok Build
- mcp-tenant-isolation in Claude Code
- mcp-tenant-isolation in Cursor
- Migration To AWS in Pi
- Mlflow in Claude Code
- Monday Crm in Claude Code
- Oracledb in Pi
- Pagerduty in Pi
- Php LSP in Grok Build
- Pyright LSP in Grok Build
- rea-agents in Claude Code
- rea-agents in Cursor
- Ruby LSP in Grok Build
- Rust Analyzer LSP in Grok Build
- safari-mcp in Claude Code
- safari-mcp in Cursor
- Sagemaker AI in Pi
- Salesforce Development in Claude Code
- Sap Hana CLI in Pi
- Save To Spotify in Pi
- Semgrep in Pi
- Spanner in Pi
- Swift LSP in Grok Build
- TypeScript LSP in Grok Build
- UI Theme Designer in Pi
- Ui5 in Pi
- Ui5 Modernization in Pi
- Ui5 Typescript Conversion in Pi
Agent versions tested
- Claude Code:
2.1.197 (Claude Code) - Codex:
codex-cli 0.163.0 - Grok Build:
grok 1.0.62 (1474f9cbdd91) - Cursor:
2026.10.16-e3cb207 - Pi:
pi 0.73.1
Run started 2026-10-27T02:03-04:00. Every failed install is retried once in a fresh sandbox before it counts. Each skill page has the log. How we test · Weekly scorecards · All daily reports
SkillMaxx Weekly
The week's install scorecard across all 5 agents, plus new skills, plugins and MCP servers and whatever changed in the official docs. Every Tuesday. (The daily report stays on the site, no daily emails.)
Loading the signup form… or subscribe on Beehiiv
Form not loading? Subscribe on Beehiiv →