Syrtis
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗352 mods for Claude Code workflow mods, ordered by the votes people give them on ClaudeMods. A good place to start: ruflo-loop-workers,ruflo-adr or code-modernization.
Each entry links to its original repository or post, and shows how to install it.
352Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗universal-modder is an MIT-licensed Claude Code plugin that can identify game engines, read real code, build mods, generate assets with fal, test in-game, and produce showcase videos.
Early: crit inside Claude Code. Comment on the conversation, your diff or a file in a pane, send the review to Claude, and read Claude's replies in threads.
A minimal Claude Code mod template that registers /my-command at session start and answers it without making any model calls.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗Cache-aware /loop workers and CronCreate background automation. Substrate plugin for every recurring task in the ruflo family.
After each turn, suggests up to three next prompts above the input. Press 1, 2 or 3 to put one in the prompt box as a draft you can edit, 0 to dismiss.

A shared Kanban board for a project, with a live one-line summary of it above the prompt.
ADR lifecycle management — create, index, reconcile, supersede, check compliance, and link Architecture Decision Records to code via AgentDB hierarchical store + causal edges (supersedes/amends/depends-on/related)
claude-reflect as a Claude Code mod: a model check on each short prompt finds reusable corrections (any language); a band above the prompt saves them to CLAUDE.md on one press

One key for 140+ AI models
bazaarlink.aiVisit sponsor ↗A Claude Code plugin that offers three modes through mode-registry: ui (low effort), api (medium) and review (max for code review and security), rewriting the main thread's effort per mode via turn.step hooks.
Official Claude Code plugin that analyzes a legacy codebase, produces an approved modernization plan, builds the new code, and proves the new behavior matches the old through script-checked evidence and independent verification.

A shared /mode switch that any plugin can offer a mode to. Shows the active mode in the prompt footer. Makes no model calls.
When Claude finishes a task that changed something, a small quiz appears above the prompt: two or three questions about what was just built, each with a button that reveals the answer and why. It checks that you understand the change, not that you remember file names. Press **Save to deck** and the questions become spaced-repetition cards in your explain-this deck.