Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add harnessprotocol/harness-kitnpx agentmods add plugins/harnessprotocol/harness-kit/marketplacegit clone --depth 1 https://github.com/harnessprotocol/harness-kitGrade A, and why
harness-kit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "harness-kit",
"owner": {
"name": "harnessprotocol"
},
"metadata": {
"description": "Claude Code skills, agents, and configuration — the parts worth sharing.",
"pluginRoot": "./plugins"
},
"categories": [
{ "slug": "research-knowledge", "name": "Research & Knowledge", "display_order": 1 },
{ "slug": "code-quality", "name": "Code Quality", "display_order": 2 },
{ "slug": "data-engineering", "name": "Data Engineering", "display_order": 3 },
{ "slug": "documentation", "name": "Documentation", "display_order": 4 },
{ "slug": "devops", "name": "DevOps & Shipping", "display_order": 5 },
{ "slug": "productivity", "name": "Productivity", "display_order": 6 },
{ "slug": "design", "name": "Design", "display_order": 7 }
],
"plugins": [
{
"name": "research",
"source": "./plugins/research",
"description": "Process any source into a structured, compounding knowledge base with refresh capability",
"version": "0.5.1",
"author": { "name": "harnessprotocol" },
"license": "Apache-2.0",
"category": "research-knowledge",
"tags": ["research", "knowledge-base", "web-scraping", "pdf", "github", "sources"]
},
{
"name": "explain",
"source": "./plugins/explain",
"description": "Structured code explainer — layered explanations of files, functions, directories, or concepts",
"version": "0.2.0",
"author": { "name": "harnessprotocol" },
"license": "Apache-2.0",
"category": "code-quality",
"tags": ["code-explanation", "learning", "walkthrough", "codebase-understanding"]
},
{
"name": "lineage",
"source": "./plugins/lineage",
"description": "Trace column-level data lineage through SQL, Kafka, Spark, and JDBC codebases",
"version": "0.3.0",
"author": { "name": "harnessprotocol" },
"license": "Apache-2.0",
"category": "data-engineering",
"tags": ["sql", "data-lineage", "kafkaWhat this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 192 lines scan A b026ef57ff98
harness-kit is a plugin published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
llm-wiki
Plugin marketplace listing 1 plugin: llm-wiki.
llm-wiki-plugin
Build and maintain an LLM-curated personal knowledge base with default local FastEmbed + sqlite-vec search, BM25 fusion, structured evidence, incremental caching, and a compiled graph layer.
mindmap-marketplace
Plugin marketplace listing 1 plugin: mindmap.
mindmap
Generate interactive mind maps from any content — with contradiction detection, gap analysis, source attribution, adaptive layouts, and a persistent knowledge atlas. Outputs interactive React artifacts or portable Markmap files.
vault-pkm
Bidirectional knowledge flow between Claude Code and Obsidian — 20 MCP tools, skills, and hooks for PKM.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.