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.
npx agentmods add plugins/firelock-ai/kin/kin-claude/plugin marketplace add firelock-ai/kingit clone --depth 1 https://github.com/firelock-ai/kinGrade A, and why
kin 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.
What it actually says
{
"name": "kin",
"description": "Kin keeps a living map of the software itself so humans and agents can understand what every change touches. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.",
"version": "0.1.0",
"author": {
"name": "Firelock",
"url": "https://kinlab.ai"
},
"homepage": "https://kinlab.ai",
"repository": "https://github.com/firelock-ai/kin",
"license": "Apache-2.0",
"keywords": [
"code-search",
"semantic-search",
"code-navigation",
"impact-analysis",
"code-review",
"mcp"
],
"interface": {
"logo": "./icon.png",
"composerIcon": "./icon.png"
}
}What 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 · 24 lines scan A b486b3a82ddb
kin is a plugin published in the GitHub repository firelock-ai/kin (47 stars, last pushed yesterday), 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 2026-08-30.
Other plugins, from other repositories
tool-gates
Permission gates for Claude Code shell, file, search, Skill, and MCP tool surfaces. Intelligent command safety, file read/write guards, and tool blocking.
tool-gates
Intelligent permission gate for Claude Code shell, file, search, Skill, and MCP tool surfaces. AST-parses Bash commands, guards file reads/writes, and blocks configured tool invocations. Defers benign asks to CC's resolver so the prompt UI shows the 'Yes, and don't ask again for X' button, while keeping a deny floor…
tree-sitter-language-pack
Parse and extract code intelligence from 371 programming languages with tree-sitter — structure, imports, symbols, and syntax-aware chunking.
scraps-migration
LLM migration workflows for moving Scraps wikis from v0 to v1. Runs version-pinned audits, converts tag and config syntax, and verifies the result with v1 lint/build.
org-mcp-server-dev
Development marketplace for org-mcp-server skills.
cranpose-marketplace
Plugin marketplace listing 1 plugin: cranpose.