Skill Claude CodeCodex
Use Agent Booster MCP tools for token-efficient code reading. Replaces Read/Grep with smartread and searchcontext to reduce token usage 5-15x. Includes background daemon for instant search and auto-indexing on file save.
Plugin Claude Code
AST + vector context router for AI coding agents — cut token costs 5-15x. Provides smartread, searchcontext, getsymbols, and routemodel MCP tools. Includes delta indexing (skips unchanged files), asymmetric embeddings for better retrieval, and an optional background daemon for instant search.
Skill Claude CodeCodex
Use Agent Booster MCP tools for token-efficient code reading. Replaces Read/Grep with smartread and searchcontext to reduce token usage 5-15x. Includes background daemon for instant search and auto-indexing on file save.
Hook Claude Code
Runs before the agent uses a tool for Read, Grep and Agent tool calls, executing booster-gate.py, booster-grep-nudge.py and booster-agent-inject.py via python3 (3 commands). From sseshachala/agent-booster.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing booster-route.py via python3. From sseshachala/agent-booster.
Hook Claude Code
Runs when a session starts, executing booster-session-start.py via python3. From sseshachala/agent-booster.
Hook Claude Code
Runs when the agent finishes a response, executing booster-stop.py via python3. From sseshachala/agent-booster.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, UserPromptSubmit, SessionStart, Stop) and 4 allowed tools.
MCP server Claude CodeCodexCursor
MCP server "agent-booster" as configured in sseshachala/agent-booster. Launched with booster serve. Needs 1 environment variable to run.
Instructions file
Claude Code instructions for sseshachala/agent-booster: Prefer booster MCP tools over native Read/Grep.
Plugin Claude Code
Conduct AI CLI — run agents, manage workspaces, and enforce AI usage policies with ConductGuard MCP. Includes conduct, conductguard-mcp, and conduct-mcp binaries.
Skill Claude CodeCodex
ConductGuard MCP — enforces AI usage policies set by your team lead. Every file-write and sensitive tool call Claude makes is checked against Guard policies. Blocked calls are logged with who, what, and when.
Hook Claude Code
Runs before the agent uses a tool for Read, Grep and Agent tool calls, executing booster-gate.py, booster-grep-nudge.py and booster-agent-inject.py via python3 (3 commands). From sseshachala/conduct-cli.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing booster-route.py via python3. From sseshachala/conduct-cli.
Hook Claude Code
Runs when a session starts, executing booster-session-start.py via python3. From sseshachala/conduct-cli.
Hook Claude Code
Runs when the agent finishes a response, executing booster-stop.py via python3. From sseshachala/conduct-cli.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, UserPromptSubmit, SessionStart, Stop) and 4 allowed tools.
MCP server Claude CodeCodexCursor
MCP server "agent-booster" as configured in sseshachala/conduct-cli. Launched with booster serve. Needs 1 environment variable to run.
Instructions file
Claude Code instructions for sseshachala/conduct-cli: Prefer booster MCP tools over native Read/Grep.
MCP server Claude CodeCodexCursor
CLI for Conduct AI — secure, govern, install agents, manage projects, run tests. Runs locally from the conduct-cli Python package.