sgrep
Local semantic and hybrid search for codebases and coding-agent history. Find implementation by intent, then recover the decisions and fixes that led to it across Claude Code, Codex, Cursor, OpenCode, and Pi sessions.
The auto-invoked alpha. Only found here.
Local semantic and hybrid search for codebases and coding-agent history. Find implementation by intent, then recover the decisions and fixes that led to it across Claude Code, Codex, Cursor, OpenCode, and Pi sessions.
Spec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 36 skills, 19 commands, 15 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
A comprehensive BigQuery plugin for Claude Code. Five integrated skill areas that activate automatically -- writing queries, designing schemas, optimizing costs, detecting anti-patterns, and navigating BigQuery-specific features.
**Trace where files came from, keep AI-agent output in the right place, and see what each task changed — locally, with evidence, and with honest uncertainty.** Built for Python and notebook work: research code, data analysis, and the piles of files AI coding
Import it from GitHub and we review every one. Merged plugins join the library with your credit. Open source, free.
Two ways in: import a GitHub repo here, or open a pull request if you prefer the git-native path.
Or submit via PR on GitHubAgentic memory for coding agents — captured from the agent's real work, injected when it acts, kept honest when it contradicts itself. One SQLite file. MCP + CLI + hooks + dashboard. No cloud.
Reusable agent skills for AI coding assistants. Compatible with Cursor, Claude Code, Codex, and 40+ agents via npx skills.
A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in any project.
A Claude Code plugin that generates infrastructure and architecture diagrams (and documentation) from your codebase using D2. Command: /d2:diagram
Claude orchestrates. OpenCode codes. You review the diff. A Claude Code skill that delegates coding tasks to OpenCode CLI and supervises the result — the same pattern as vibe-skill and gemini-skill.
Ask for a diagram. Get a hand-drawn animation — one HTML file, one seamless-loop GIF.
Make math in Claude Code and Codex legible. Terminal coding agents do not render LaTeX.
A plugin for pi, Claude Code, and OpenCode that guides AI agents through disciplined Test-Driven Development and Clean Code practices. Note that currently this is WORK IN PROGRESS! I'm not even trying to keep it stable or tested.
An agentic software engineering method: AI agents do the building, the build enforces the rules that must always hold, a person decides only at the gates, and the method measures its own cost in human turns.
A governed multi-agent SDLC pipeline for Claude Code and Qwen Code — a ground-up rewrite of ai-sdlc-harness.
You're a solopreneur. You have ideas, ambition, and not enough hours in the day.
A one-command setup for a richly decorated Claude Code statusline with Caveman mode baked in. Interactive installer lets you pick all components or only the ones you want.
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.
A self-learning, project-scoped sprint workflow for Claude Code. booping turns a feature idea into a durable, on-disk loop — groom → develop → retro → learn — that uses sub-agents to avoid context rot, with an optional second-model cross-review of every plan.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic