✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation
active 2026-02-12 → 2026-03-05 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 22 days from 2026-02-12 to 2026-03-05. Pushes: 14 total, peak 4 in a day. Pull requests: 27 total, peak 8 in a day. Issues: 11 total, peak 9 in a day. Comments: 19 total, peak 11 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| TerminalGravity | 82 | 14 | 27 | 19 |
Recent activity
Latest issues, pull requests and releases
- Pull request#124TerminalGravity2026-03-05 19:44
- Pull request#120TerminalGravity2026-03-05 17:18
- Issue comment#37TerminalGravity2026-03-05 16:24docs: reorder quickstart — npm install first, add init wizard step
- Issue comment#53TerminalGravity2026-03-05 16:23fix: move pattern-boost logic into triagePrompt
- Issue comment#62TerminalGravity2026-03-05 16:23test: add unit tests for prompt_score scoring logic
- Issue comment#75TerminalGravity2026-03-05 16:23fix: prompt_score scope bug + 11 unit tests
- Issue comment#95TerminalGravity2026-03-05 16:22fix: convert remaining run() shell syntax to array args
- Issue comment#111TerminalGravity2026-03-05 16:21fix: resolve all remaining shell syntax in run() calls
- Pull request#112TerminalGravity2026-03-05 12:06
- Pull request#104TerminalGravity2026-03-05 07:45
- Pull request#103TerminalGravity2026-03-05 07:14
- Pull request#101TerminalGravity2026-03-05 05:16
- Issue#89TerminalGravity2026-03-05 05:14Several tools pass shell syntax to run() which uses execFileSync
- Issue comment#89TerminalGravity2026-03-05 05:13Several tools pass shell syntax to run() which uses execFileSync
- Pull request#100TerminalGravity2026-03-05 04:46
- Issue comment#94TerminalGravity2026-03-05 02:14fix: replace shell syntax in run() calls with proper APIs
- Issue comment#93TerminalGravity2026-03-05 02:14fix: replace shell syntax in run() calls with runShell/Node APIs
- Pull request#95TerminalGravity2026-03-05 01:46
- Issue comment#92TerminalGravity2026-03-05 00:47docs: add .preflight/ example config files with annotations
- Issue comment#91TerminalGravity2026-03-05 00:20fix: use shell() for commands needing pipes/redirects (closes #89)
- Pull request#90TerminalGravity2026-03-04 23:46
- Issue comment#89TerminalGravity2026-03-04 23:21Several tools pass shell syntax to run() which uses execFileSync
- Pull request#86TerminalGravity2026-03-04 22:14
- Issue comment#79TerminalGravity2026-03-04 21:47test: add 17 unit tests for prompt_score scoring logic
- Issue comment#80TerminalGravity2026-03-04 21:46fix(ci): fallback to --ignore-optional when sharp install flakes
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.