A Chinese-language plugin focused on making conversations, commits, pull requests, documents, and comments sound more natural and less machine-written. It is described as leaving code logic unchanged and being enabled by default.
★not rated 1 2mo agoA
tokens not measured
originalMIT
The Good, the Bad and the Ugly — tiered multi-agent orchestration for Claude Code. The Good (brain) plans and verifies, the Bad (judgment executor) handles work needing taste, the Ugly (mechanical executor) does the grunt work — in parallel herdr panes with fenced scopes.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Switch Claude Code between Anthropic direct and custom LLM gateway profiles via slash commands. Bring-your-own-URL, bring-your-own-key, zero secret material stored in plugin files.
Discover and call paid AI capabilities via a two-tier loop — vetted multi-step skills first, then a federated x402 / MPP endpoint catalog (image/video/audio generation, translation, web scraping, data enrichment, real-time data, on-chain actions). Payments settle from your own Circle Agent Wallet (MPC self-custody …
★not rated 1
changed 3d agoA
tokens not measured
originalApache-2.0
Universal loop-engineering harness: machine-verifiable stop conditions, cross-model maker/checker (Codex maker, Claude checker), disk-based loop memory, reversibility×impact decision gates that keep human approval to irreversible actions while auto-pushing reversible work-branch commits, autonomous replan on stalls, a.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Arcjet is the runtime security platform that ships in your AI code. Detect prompt injection, authorize agent tool calls, redact sensitive data, and block bots and abuse. Real-time security building blocks you call inside your app, before an action happens.
★not rated 1 4d agoA
tokens not measured
originalApache-2.0
Verbatim recall across Claude Code sessions, plus a gate that stops oversized skills from flooding the prompt. Pure Node, no dependencies, no API calls.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Automatically filters angry, hostile, and profane language from user prompts before they reach Claude. Preserves intent while replacing hostility with constructive phrasing.
Generate structured AI handoff documents from session context. Captures what was done, what failed, and what's next — formatted for the next AI agent to pick up seamlessly.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Scaffold standard-compliant repos with /new-repo, and apply the RepoKit standard (conventions + pre-commit/pre-PR checklists) while working in any compliant repo.
★not rated 1 1mo agoA
tokens not measured
originalApache-2.0
Front desk for setting up automation in Claude Code — recurring loops, finish-line goals, and scheduled cloud routines. Picks the right native primitive (/goal, /loop, scheduled tasks, /schedule routines) and configures it safely with verifiable finish lines, turn caps, machine-vs-cloud placement, and tight routine…
Turn your Claude Code + VS Code Copilot Chat + Codex sessions into per-project typed memory — episodic / semantic / procedural / core memory, a personal entity wiki, and distilled Q&A — then auto-load the project primer at the start of every session so a new session already knows the project (architecture, setup…
★not rated 1
changed 14d agoA
tokens not measured
originalMIT
Autonomous TODO workflow: refine an idea into one structured TODO item, then a git-hook chain plans → implements (subagent team + deterministic gate, isolated worktree, never auto-merged) → reviews it. Language-agnostic, config-driven, bootstrapped into any repo.
★not rated 1 2mo agoA
tokens not measured
originalMIT