Student edition of the completion harness - blocks writes to originals, permanent deletes and kill-by-name, and checks every 'done' claim against a fresh verify receipt of the project's completion-condition contract (harness.contract.json). Needs Python 3.8+.
Plugin harness-lite from marketplace korean-humanities in hw725/korean-humanities. Commands read from the repo's manifest — 13 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
harness-lite완료 조건 계약(harness.contract.json)을 만들고 확인하는 수강생판 하네스 안내. 사용자가 《완료 조건 만들어 줘》·《계약 만들어 줘》·《검증 장치》·《하네스》를 말하거나, harness-lite 훅이 《verify 하세요》·《계약 만들기》를 알렸을 때 쓴다.
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" lite_pretool.py
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" full_review_prompt.py
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" lite_stop.py
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" full_review_stop.py
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" read_range_stop.py
Korean humanities research methods for Claude Code - hanmun source criticism, hermeneutic argument planning, humanities peer review, academic English editing, and per-paper structure analysis notes. The research skills are prompt-only; the bundled CJK text helpers and the structure checker are optional, and two of them need pip install regex.
4 skills
Recover gugyeol (口訣) characters and old Hangul in Korean academic PDFs/HWPX that extract as broken (cid:N) or PUA codepoints. Mapping tables bundled; optional pip install pymupdf for PDF input.
1 skill
Self-serve KCI citation network builder for Korean humanities - give a keyword, collect citation edges via the KCI reference OpenAPI (free data.go.kr key), optionally render Obsidian notes. Stdlib-only scripts, no LLM calls.
1 skill
Build your own year x field KCI corpus (no API key; rate-limited collection with a user-editable journal profile - see the robots notice in SKILL.md) and generate hallucination-resistant Korean-studies trend reports - topic clusters, representative-paper candidates, journal breakdowns. Stdlib-only, no LLM calls.
1 skill
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
7 skills · 1 command · 3 agents
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
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
9 skills · 9 commands · 11 agents · 1 MCP server
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
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.