-
-
Notifications
You must be signed in to change notification settings - Fork 119
AgentLint
AgentLint is an automated auditing system that inspects agent configurations, plugin manifests, tool definitions, and system prompts for issues, violations, and best-practice gaps.
AgentLint runs 29 checks across 4 categories:
| Category | Checks | Description |
|---|---|---|
| Agent Config | 9 | Name length, description presence, system prompt validation, tool count, maxTurns range, provider validity, dangerous tool audit |
| Tool Definitions | 10 | Name length, description quality (action verbs, ambiguous phrasing), parameter count and descriptions, capability declarations |
| Plugin Manifests | 6 | Version presence, capability scoping, WASM runtime warnings, excessive capability detection |
| System Prompts | 4 | Instruction clarity, conflicting directives, token efficiency, unsafe patterns |
cortex agent lint check <agent-id> # Audit agent config, tools, plugins
cortex agent lint config # Show lint configurationOutput shows pass/warning/error counts with per-issue suggestions and severity badges.
| Method | Path | Description |
|---|---|---|
GET |
/api/agentlint/check?agentId= |
Run checks for a specific agent (defaults to active agent) |
POST |
/api/agentlint/check |
Run checks with custom config |
AgentLint is integrated into the Agent Manager page as a 🔍 AgentLint tab alongside "Agents" and "Sub-Agent Types". The tab lazily fetches /api/agentlint/check?agentId=<id> for the currently active agent and renders summary cards and issue list inline. A Re-run button allows on-demand re-execution.
AgentLint Results:
Total checks: 29
✅ Passed: 28
⚠️ Warnings: 3
❌ Errors: 2
Issues:
⚠️ tool_desc_quality: agent-tool has generic description (avoid "useful", "helpful")
⚠️ system_prompt_length: system prompt exceeds 4000 tokens
❌ missing_tool: declared tool 'web_search_new' not found in registry
src/agent/agentlint.ts — contains all check functions, severity scoring, and the runAgentLintChecks() orchestrator.
- Configuration — Agent and provider configuration
- Adding a Tool — Tool definition best practices
- Plugin System — Plugin manifest standards
CortexPrism — Open-source AI agent operating system · Discord · Apache 2.0 License · Built with Deno 2.x + TypeScript
- Agent Loop
- Built-in Agents
- Metacognition
- Memory System
- Skills System
- Sub-Agents
- Built-in Tools
- Code Intelligence
- Code Sandbox
- Cross-Agent Context Protocol
- Prompt Lab
- PKM Assistant
- Voice Pipeline
- Computer Use
- Browser Tool
- Git & GitHub
- Scheduler & Jobs
- Dashboard
- Observability
- A2A Protocol
- MCP Gateway
- Distributed Nodes
- Memori Checkpoints
- Eval System
- Workflow Engine
- Triggers
- Projects
- TUI
- Glossary
- Update System
- Chrome Bridge
- Swarm
- AgentLint
- Model Benchmarking
- Smart Context
- Cost Optimizer