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.
git clone --depth 1 https://github.com/Stahldavid/sensegrepWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/stahldavid/sensegrep/sensegrep-cursor)<a href="https://agentmods.dev/plugins/stahldavid/sensegrep/sensegrep-cursor"><img src="https://agentmods.dev/badge/plugins/stahldavid/sensegrep/sensegrep-cursor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/stahldavid/sensegrep/sensegrep-cursor"><img src="https://agentmods.dev/badge/plugins/stahldavid/sensegrep/sensegrep-cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sensegrep 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 20d ago.
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": "sensegrep",
"version": "1.19.0",
"description": "Semantic code search for AI agents. Search code by meaning, not text patterns. Replaces grep/ripgrep for 95% of code exploration tasks.",
"author": {
"name": "sensegrep"
},
"homepage": "https://github.com/Stahldavid/sensegrep",
"repository": "https://github.com/Stahldavid/sensegrep",
"license": "Apache-2.0",
"keywords": [
"code-search",
"semantic-search",
"ast",
"tree-sitter",
"embeddings",
"mcp",
"refactoring",
"duplicate-detection"
],
"category": "developer-tools",
"tags": [
"search",
"semantic",
"code-intelligence",
"mcp"
],
"logo": "assets/logo.png",
"rules": "./rules/",
"skills": "./skills/",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 46 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 20d ago Changed 359b7ed448eb
- 21d ago First seen · 33 lines scan A 24608feff890
sensegrep is a plugin published in the GitHub repository Stahldavid/sensegrep (1 stars, last pushed 20d 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 2026-09-24.
Other plugins, from other repositories
cocoindex-code
AST-based semantic code search via the ccc CLI. Bundles the ccc skill; Grok installs also activate a SessionStart index hook and MCP server (disable either for skill-only).
codanna-toolset
Codanna toolset for Claude Code: x-ray (semantic search + relationship traversal with 3D neighbourhood, radial tree and edge-bundle views) and graph (the whole index as a module disc with hubs at the centre, timeline and heatmap). Needs the codanna CLI.
codebase-index
Semantic code search and codebase graph tools for Claude Code.
cocosearch
Local-first hybrid semantic code search with dependency graphs and cross-repo search. Powered by CocoIndex, Tree-sitter, pgvector, and Ollama.
kin
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.
cix
Semantic code search for Claude Code. Requires a self-hosted cix (CodeIndeX) server — free, MIT, 10-minute install (https://codeindex.app) on your machine, LAN box, or GPU server; the plugin is the client. Ships the cix CLI, slash commands (incl. cix file / cix tree for external projects), behavioral hooks, the cix sk.