Stop AI agents from doing things you didn't ask for.

A toolkit of skills, templates, and guides for bootstrapping AI-agent-friendly projects. Started from Anthropic's Claude Code engineering patterns, extended with a per-project self-improvement loop and more.

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.

Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.

Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

Agentic Software Engineering (ASE)

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Vendor-neutral control-plane contract for coding agents: a normalized ToolCallEvent/Verdict schema with per-agent adapters (Claude Code, Codex, Amp, Gemini CLI) and a conformance suite.

📋 Prompt-engineering and project-roadmap plugin that crafts professional xml prompts and picks, surveys, and tracks your next tasks.

A Claude Code plugin that solves the same problems as community frameworks (GSD, BMAD, Ralph, Agent OS) — but using the tool's native architecture instead of fighting it.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

Live deck of Claude Code and Codex agents — watch tool calls, token spend and every Claude Code subagent on one calm canvas. Also available as npx ccdeck and npx agent-dag.

Local cockpit for the Claude Code CLI — multi-tab terminal, full config surface, scheduler, voice dictation, and live observability.

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

一个自主的高级智能伙伴，不仅分析问题，更持续工作直到完成实现和验证。

"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green and no TODOs are left behind.

Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and knowledge distillation

Dashboard for monitoring claude code sessions.

Build with Claude Code without your brain going numb — a plugin that quizzes you on the code it just wrote and gates the session until you pass.

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.

A Claude Code plugin that stops vague prompts before they run. Detects your stack, asks targeted questions, and forges a structured prompt. Zero credits wasted.

🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace