Run a long multi-phase build to completion across automatically chained Claude Code sessions, refreshing context before quality degrades. Sandboxed by default, with a consented full-trust mode for work that needs SSH or the network.
★not rated 1 5d agoA
tokens not measured
originalMIT
A knowledge-precipitation harness for Claude Code — a disciplined multi-stage delivery workflow that captures durable learning and matures it through reuse. The workflow is the pipe; knowledge is the moat.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Casts a spec and a CLI from closed apps that have no API. Drop an APK, IPA, EXE, DMG or traffic capture; a three-pass research method with built-in blind-spot diagnosis turns it into a feature spec, a reconstructed OpenAPI document, and optionally a CLI.
Orchestration skills for Vibe Kanban: plan → ship → link → review → merge with wave-based dispatch, executor routing (T0-T4), and autonomous fix loops.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Instagram downloader — CLI + MCP server. Six tools, three prompt templates, session capture against your real browser profile via the Chrome M144 chrome://inspect toggle.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Notification sounds for Claude Code on Windows: distinct cues for task-complete, needs-input, and error, played only when the terminal is backgrounded.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Agent skills for running a Radarr/Sonarr media stack: API connection doctrine and the container-path trap, the instance map that stops profile-id guessing, quality profiles and the cutoff settings that cause endless upgrade storms, monitoring drift and guarded delete-then-regrab, the search-to-import chain, and the…
★not rated 1 1mo agoA
tokens not measured
originalMIT
End-of-Turn Queue — queue prompts with /queue:add and each is delivered back to Claude at the end of the turn, after it fully finishes its work, never mid-task. A FIFO prompt queue for Claude Code, built on a self-terminating Stop hook.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Claude Code plugin for Java development with Eclipse JDT LS integration, 12 automated hooks for Maven/Gradle builds, linting (SpotBugs, Checkstyle), formatting, and testing (JUnit).
★not rated 1 1mo agoA
tokens not measured
originalMIT
SpecSeal — specs, sealed: an implement/review agent chain with hook enforcement, an evidence ledger with drift detection, and a tool-agnostic review handoff protocol.
★not rated 1
changed todayA
tokens not measured
originalMIT
Cross-platform desktop notification (Windows/macOS/Linux) when Claude Code finishes a turn. Windows path is ThreatLocker-safe (inline PowerShell). Configurable agent name, session label, icon, and optional sound.
Test, validate, and benchmark performance of LSP servers using only YAML. Configs for benchmarks, response assertions, multi-file consistency checks, file-edit sequences, lifecycle tests, version comparisons, and LSP session management — restart per benchmark (cold) or reuse one initialized session across steps (warm).
★not rated 1 4mo agoA
tokens not measured
originalMIT