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/sseshachala/conductai/booster/plugin marketplace add sseshachala/conductaigit clone --depth 1 https://github.com/sseshachala/conductaiGrade A, and why
agent-booster 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-booster — 100% identical, 0 lines differ
What it actually says
{
"name": "agent-booster",
"version": "0.2.19",
"description": "AST + vector context router for AI coding agents — cut token costs 5-15x. Provides smart_read, search_context, get_symbols, and route_model MCP tools. Includes delta indexing (skips unchanged files), asymmetric embeddings for better retrieval, and an optional background daemon for instant search.",
"author": "Sudhi Seshachala",
"homepage": "https://conductai.ai/tools/agent-booster",
"repository": "https://github.com/sseshachala/conductai",
"license": "MIT",
"keywords": ["mcp", "tokens", "claude", "ast", "context", "ai", "agents"],
"install": {
"steps": [
{
"type": "shell",
"command": "pip install 'agent-booster[full]'",
"description": "Install agent-booster with embeddings + file watcher"
},
{
"type": "shell",
"command": "booster init claude",
"description": "Wire MCP server, hooks, and CLAUDE.md for this repo"
},
{
"type": "shell",
"command": "booster start",
"description": "Start background daemon — keeps model warm, auto-indexes file changes"
}
]
}
}
What ships with it
2 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 30 lines scan A dee6677aae72
agent-booster is a plugin published in the GitHub repository sseshachala/conductai (24 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 2026-08-30.
Other plugins, from other repositories
aiforge
为 Claude Code 智能推荐和注入最相关的 skill.
asset-pipeline
Refine and process generated game assets: animated spritesheets, Aseprite parsing, sprite-sheet pipelines, pixel-grid snapping, and image-to-procedural-Three.js props.
laguagu
Next.js + AI SDK agent skills.
flickies
Self-hosted video toolkit — lipsync, face restore, and ffmpeg ops (trim, concat, transcode, scale) via REST and MCP.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.