Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
15 production writing-style skills for AI agents: 8 measurable frameworks (plain language, ASD-STE100, AP journalism, GOV.UK) and 7 character voices, as portable SKILL.md files.
Mistake-proof your code, your pipeline, and your agents. Audits code for mistakes that are possible, designs APIs where misuse cannot be expressed, installs guardrails, and turns incidents into devices that prevent recurrence.
A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log — so you can watch progress without reading the transcript.
Adversarial multi-model code review and model dispatch. Orchestrates Claude, Codex CLI, and Gemini CLI for cross-examined code review with 5 specialized reviewers.
Language-specific development experts covering 13 programming languages including Python, TypeScript, JavaScript, Go, Rust, C++, and more. Includes refactoring specialist.
A shared add-on for frontend development teams, with frontend instructions, helper agents, automated hooks, and connections to design tools such as Figma and Sketch. It saves reports as Markdown files.
A full-fledged Claude Code multi-team orchestration pattern that uses only the native agent teams feature - by decoupling the role of agent-as-leader and agent-as-spawner, a wide range of undocumented capacities for complex layered teams are unlocked.
Train Claude in the practice of meditation, by compelling Claude to observe its own thought patterns. Rather than the standard loop: Act -> Observe -> Act; this plugin introduces a second observation phase: Act -> Observe(1) -> Observe(2) -> Act. Observe(2) is a meta-cognitive act of observation of Observe(1). As with.
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits. A passthrough proxy that stabilizes the exact request bytes CC emits — deterministic tool order, canonical JSON, volatile-content relocation — plus the env hardening that stops a custom endpoint from busting the cache.
Complete 21-phase local business SEO audit system with 6 parallel agent team. Project-based directory structure (projects/[business-slug]/). 8 Python scripts for automation. LOCAL-IMPACT (60-item) and SERP-TRUST (50-item) proprietary scoring frameworks. AI visibility & GEO (AIO, ChatGPT, Perplexity, Gemini, Copilot).…
Structured agentic development methodology - from issue analysis to merge.
20 3mo 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: