A mod that runs the yomiyasu linter on the Japanese body of gh pr / gh issue create, edit and comment and of git commit before the Bash tool runs them, and sends the command back to the agent with the offending lines when the text breaks the rules. Fail-open: without the linter it lets everything through.
1 on GitHubby Seiya Kawamurav0.1.0MITupdated 1 month ago
/
Plugin yomiyasu-gate from marketplace claude-ship in insession-space/claude-ship. Commands read from the repo's manifest — 1 month ago.
What it installs
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
A workflow that turns a request into a GitHub Issue and implements it in the same session until every acceptance criterion is met, verification is green, and the review has zero findings. It decides the goal (Issue / implementation / PR / merge) once before starting and stops there.
An add-on to ship-session that lets Jev (TypeSafe AI's System One model) decide the goal from the request and skip the Phase 0 question when its confidence is high. Optional and fail-open: without TYPESAFE_API_KEY, or when the API fails, it behaves exactly like ship-session. Requires ship-session.
Design templates for Artifacts, picked by purpose: a plan becomes a landing page, a review a technical report, an investigation a report or a dashboard, shipped work an implementation report. One dark-first base and a no-slop list keep pages consistent.
Breaks a task into a graph of nodes and edges and runs it deterministically in parallel with the Workflow tool. It shows the graph design for approval first and resumes midway on failure.
A mod that shows the progress of the issue you are working on: when the agent reads or edits a GitHub issue with gh, it reads the issue's checklists back from GitHub and shows above the prompt how many acceptance criteria are done and which remain.
A mod that shows each running subagent and teammate as a character: one row per agent in a band above the prompt (face, type, task, current tool, elapsed time), and their faces at the head of the spinner line. Each agent type has its own face.
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
Optional mods companion for claude-seo (needs Claude Code 2.1.287+). A spend guard that holds paid SEO API calls against the claude-seo budget, and zero-token /seo-spend and /seo-doctor commands.
AgriciDaniel/claude-seo 28,747
Maintain yomiyasu-gate?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.