Language-agnostic baseline rules for Claude Code: minimal-change principle, Conventional Commits, documentation conventions, and Context7 MCP guidance for library lookups.
Baseline rules for Claude Code: minimal-change principle, Conventional Commits, documentation conventions, and Context7 MCP guidance for library lookups.
/plugin marketplace add dominik-rehse/language-agnostic-agent-setup
/plugin install language-agnostic-agent-setup@language-agnostic-agent-setup
That's it — there is no per-project setup. A SessionStart hook injects the
rules in rules/ into the session context live from the plugin, so the rules are
active from the first session and a plugin update applies on the next session.
Nothing is vendored into the project, so nothing goes stale.
(Legacy installs that vendored these rules into .claude/rules/*.md still work —
the hook skips any rule already present there to avoid double-loading. Delete the
vendored copy to switch that rule to live injection.)
/language-agnostic-agent-setup:code-simplifier — review the whole codebase
and apply clarity and consistency simplifications while preserving behaviour.
Pass a path to scope the pass to a subtree. Best run on a capable model, since
it reasons across the entire repository./plugin marketplace update language-agnostic-agent-setup
/plugin update language-agnostic-agent-setup@language-agnostic-agent-setup
Start a new session afterwards; the rules load fresh from the updated plugin. The
plugin is versioned — bump version in plugin.json to ship a release.
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.
npx claudepluginhub dominik-rehse/language-agnostic-agent-setup --plugin language-agnostic-agent-setupSpec and test driven development for Claude Code. Enforces spec-first, one-test-at-a-time TDD via slash commands, a PreToolUse guard hook, a git pre-commit gate, and a Stop-hook coverage audit.
Bun + TypeScript stack rules: TS conventions, formatting, bun:test testing, security, Bun-first tooling, and Bun runtime / built-in API guidance.
hone is a development model where a human writes a short Plan and an automated loop then builds, verifies, consolidates, reviews, and lands each change unattended in a git worktree; a scheduled garden loop (/hone:garden) cuts staleness between changes. The repo keeps only durable truth that cannot go stale, and every cycle deletes something. Enforced by a PreToolUse guard, a Stop-hook gate and nag, two fault-finding critics, and default-on land gates for irreversible changes (authority) and real-environment proof.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Persistent coding companion for Claude Code, Pi, and Oh My Pi. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses