By Eigenwise
Project rules in a Markdown file that Claude re-injects right when they apply: every prompt, or just before it edits a matching file. Edits apply on the next prompt, no restart. A SessionStart hook injects the always-on rules once as a fallback, and it's a way to tell whether per-prompt injection is actually wired.
Create or edit a live-rules rule: a frontmatter-plus-body section in the project's live-rules file (.claude/live-rules.md by default, or wherever LIVE_RULES_PATH points) that gets injected into Claude's context automatically when it applies. Use when the user asks to "add a rule", "create a rule", "make a rule that...", "add a coding guideline/guardrail/convention", "enforce that ...", "always do X", "whenever I edit *.tsx do Y", "when I work in packages/api do Z", "when my prompt mentions 'deploy' remind me to ...", "load my codebase map into every session", "keep file X in front of you", or "set up live-rules". Picks the right scope (global, path/glob, directory, or prompt-keyword) and writes valid frontmatter, including an `include:` payload to inject a live file's contents. To list, audit, enable, or disable existing rules instead, use manage-rules.
Inspect and maintain the live-rules in the project's live-rules file (.claude/live-rules.md by default, or wherever LIVE_RULES_PATH points): list every rule with its scope and status, audit them for problems (broken frontmatter, globs that match nothing, duplicates, oversized bodies, conflicts), enable or disable a rule, or explain which rules are currently active. Use when the user asks to "list my rules", "what rules are active", "show live-rules", "audit my rules", "disable the X rule", "enable the X rule", "turn off that rule", "why did Claude get that instruction", or "clean up my rules". To create or edit a rule, use add-rule instead.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A small, growing marketplace of Claude Code plugins by Eigenwise.
Sharp little tools for Claude Code, kept in one shed. 🛠️
| Plugin | What it does |
|---|---|
| workspace-init | Start here. Sets up a project's .claude/ end to end: a short interview, then a populated settings.json, a tailored live-rules.md, a codebase map, and structure notes, wired around the plugin-reload boundary and verified firing. Orchestrates the other three plus the built-ins, and bakes in a self-improvement loop so the setup keeps sharpening itself. |
| codebase-mapper | Keeps a small, self-updating map of your codebase and loads it into every Claude session, so Claude already knows how your project is built when you start working. |
| live-rules | Inject your own rules into Claude's context the moment they apply: global rules on every prompt, file-type and directory rules right before an edit, keyword rules when your prompt matches. Edit a rule, it applies on the next prompt. |
| sidequest | A Trello-light quest log for Claude Code. Side issues you mention mid-task get captured as tickets on the spot, with pasted images attached, then managed on a live, self-hosted Kanban dashboard spanning every project you work in. Category-based routing picks a concrete model and reasoning effort per ticket, with category and global fallbacks. |
| switchboard | Complexity-scored model and effort routing. Score a task 1-10 and switchboard derives which model tier should run it and how hard it should think, then hands the work to a named executor subagent at exactly that tier. |
More tools will move into the shed over time.
/plugin marketplace add Eigenwise/eigenwise-toolshed
/plugin install workspace-init@eigenwise-toolshed
/plugin install codebase-mapper@eigenwise-toolshed
/plugin install live-rules@eigenwise-toolshed
/plugin install sidequest@eigenwise-toolshed
/plugin install switchboard@eigenwise-toolshed
Then run /reload-plugins (or restart Claude Code) and you're set. It's a public marketplace, so there's no auth to deal with.
Quickest start: install workspace-init, reload, then in any project just ask "set up a Claude workspace here". It sets the other three up for you.
The other three plugins each set up one thing. workspace-init sets up the whole workspace, and wires them together for you. You install it, ask it to set up a workspace in a project, and it:
.claude/settings.json enabling the right plugins for that stack (the toolshed core plus
a language server, a frontend or docs plugin, and so on), then pauses at the reload boundary so
the plugins actually load..claude/live-rules.md (craft baseline plus stack-specific rules) and short
structure notes, and delegates the codebase map to codebase-mapper and CLAUDE.md to the built-in
/init.npx claudepluginhub eigenwise/eigenwise-toolshed --plugin live-rulesSkills plus explorer and reviewer subagents for building, scaffolding, debugging, understanding, and auditing applications with the Atomic Agents Python framework. Includes the umbrella `framework` skill, action-oriented `create-atomic-schema` / `create-atomic-agent` / `create-atomic-tool` / `create-atomic-context-provider` skills, the `troubleshoot` diagnostic skill, the `new-app` scaffolder (emits AGENTS.md + CLAUDE.md), progressive-disclosure reference material for prompts, orchestration, memory, hooks, providers, project structure, and testing, and isolated-context subagents for codebase mapping and code review.
MCP gateway that lets any web app expose typed actions to Claude over WebSocket — no browser automation. Reverse-connection architecture: the gateway is a pure WebSocket client that discovers apps via `~/.tesseron/tabs/` — no fixed ports, no env vars. Plus a `framework` skill for the Tesseron mental model, a `tesseron-docs` skill that calls the published `@tesseron/docs-mcp` server for authoritative chapter-and-verse spec lookups, a `tesseron-dev` skill that picks the right consumer package (`@tesseron/react` for React, `@tesseron/svelte` for Svelte 5, `@tesseron/vue` for Vue 3, `/server` for Node, `/web` for any other browser context) and inserts the canonical API at the project's entry point, and `tesseron-explorer` / `tesseron-reviewer` skills for mapping and auditing Tesseron codebases.
Set up and maintain a Claude Code workspace: initialize project-side configuration, check and update Toolshed plugins, diagnose local health, and run retrospectives.
A Trello-light quest log for Claude Code. The side issues you mention mid-task ("oh, and the contact form doesn't send") get captured as tickets on the spot, with any pasted images attached, and managed on a live, self-hosted Kanban dashboard that spans every project you work in.
A self-maintaining codebase map: atomic docs Claude loads at the start of each session and keeps in sync as the code changes. Any stack; greenfield or existing.
Automatic context engineering — observes your coding sessions and generates rules, suggestions, skills, and hooks so Claude gets smarter on your codebase over time
Hybrid RAG rule retrieval + session-aware workflow enforcement. Injects relevant coding rules via a 5-stage pipeline (BM25 + vector + graph traversal + reciprocal-rank fusion) and enforces mode-based workflow gates (plan -> tests -> implementation).
Set up and maintain a Claude Code workspace: initialize project-side configuration, check and update Toolshed plugins, diagnose local health, and run retrospectives.
Development workflow bundle (includes peer + extract-rules + dev-workflow + rules-review + tidy + prose-polish + mobpro)
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems