Team operations pipeline — EM triage with strategic lens (depth-adaptive routing, team context cache), project pulse updates, codebase exploration, issue decomposition, structured Linear management, EM plan/project review (keystone verification + cross-model pressure-test), and on-demand cross-model second opinion via.
★not rated 3
changed 6d agoA
tokens not measured
originalMIT
Query Trackio projects, runs, and metrics using the trackio CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system met.
Scientific narrative reviews and draft audits with live literature discovery, verified bibliographic records, independently checked assertions, evidence receipts, and explicit certainty and access limits. Outputs include chat and journal PDFs.
★not rated 3
changed 11d agoA
tokens not measured
originalMIT
Your agent has no idea what time it is. chronos reads the transcript it already writes: a live clock on your statusline, a warning the moment it repeats a failed command, and an honest answer to where the session went.
★not rated 3 14d agoA
tokens not measured
originalMIT
Project tracking, task management with kanban boards, bug logging, decision records (ADR), session management, and engineering traceability via Obsidian. Auto-tracks sessions, actions, bugs, and commits via hooks.
★not rated 3 4d agoA
tokens not measured
originalMIT
Triage user-felt bugs, pull evidence (screenshots, console logs, network requests), check blast radius, and dispatch fix PRs — all from your AI coding agent. Mushi sees what users feel; Sentry sees what code throws.
★not rated 3 4d agoA
tokens not measured
originalMIT
Independent authorization plane for AI agents — approve, escalate, or deny spend, tools, credentials, and provisioning. Wires the hosted wallet MCP; the host must ask before acting.
On Claude Fable 5.1 (or Opus), Claude's helpers (subagents) inherit your expensive model and can start helpers of their own — one web research pass can burn a session's usage limit in minutes, and an instruction to be frugal doesn't survive context compaction. frugal-subagents builds the limits in: helpers run on a…
★not rated 3 12d agoA
tokens not measured
originalMIT
Prime a repository for quality software engineering — installs direction-focused intelligence topics for Arrange–Act–Assert tests, Clean Code, Clean Architecture, comment-free code, the boy scout rule, and the detected stack.
Your real, logged-in Chrome as an MCP server: navigate, read, fill, audit, diff and record in the browser you already use. ChromeOS included, no debugger permission. Ships the chrome-bridge skill (recipes) and the zero-token CLI.
★not rated 3 2d agoA
tokens not measured
originalMIT
Post and schedule social media content to all top platforms (Instagram, TikTok, YouTube, LinkedIn, X, Facebook, Threads, Pinterest, Bluesky, Telegram, Discord) from Gemini CLI. 33 tools: publishing, media upload, AI captions, campaigns, analytics.
★not rated 3 5d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: