errors

An application error flow that shows how errors from core services reach command-line and MCP tool handlers. It also shows how those handlers format or map errors for users and protocols.

In plain words
What is it for?
Use it to trace errors such as missing projects, unfinished tasks, file-read failures, and missing parameters through the application. It helps maintain consistent error codes and outputs for CLI commands and MCP tools.
Why use it?
It gives developers one place to understand where errors are created, caught, formatted, and returned. This reduces confusion when tracing failures across different interfaces.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/chriscarrollsmith/taskqueue-mcp/errors
Clone the repo
git clone --depth 1 https://github.com/chriscarrollsmith/taskqueue-mcp

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00615
Opus 5 $0.00000 $0.00308
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00061

Measured 2d ago against content hash cba4f12da133, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

errors 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 2d 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.

.cursor/rules/errors.mdc · 57 lines

What it actually says

Error Flow

graph TD
    subgraph Core_Logic
        FS[FileSystemService: e.g., FileReadError] --> TM[TaskManager: Throws App Errors, e.g., ProjectNotFound, TaskNotDone]
        TM -->|App Error with code ERR_xxxx| CLI_Handler["cli.ts Command Handler"]
        TM -->|App Error with code ERR_xxxx| ToolExec["toolExecutors.ts: execute"]
    end

    subgraph CLI_Path
        CLI_Handler -->|App Error| CLI_Catch["cli.ts catch block"]
        CLI_Catch -->|Error Object| FormatCLI["client errors.ts formatCliError"]
        FormatCLI -->|"Error [ERR_xxxx]: message"| ConsoleOut["console.error Output"]
    end

    subgraph MCP_Server_Path
        subgraph Validation_Layer
            ToolExecVal["toolExecutors.ts Validation"] -->|App Error, e.g., MissingParameter| ExecToolErrHandler
        end
        
        subgraph App_Execution
            ToolExec -->|App Error with code ERR_xxxx| ExecToolErrHandler["tools.ts executeToolAndHandleErrors catch block"]
            ExecToolErrHandler -->|Map AppError to Protocol Error or Tool Result| ErrorMapping
            ErrorMapping -->|"If validation error (ERR_1xxx)"| McpError["Create McpError with appropriate ErrorCode"]
            ErrorMapping -->|"If business logic error (ERR_2xxx+)"| FormatResult["Format as isError true result"]

            McpError -->|Throw| SDKHandler["server index.ts SDK Handler"]
            FormatResult -->|"{ content: [{ text: Error [ERR_xxxx]: message }], isError: true }"| SDKHandler
        end

        SDKHandler -- Protocol Error --> SDKFormatError["SDK Formats as JSON-RPC Error Response"]
        SDKHandler -- Tool Result --> SDKFormatResult["SDK Formats as JSON-RPC Success Response"]

        SDKFormatError -->|"{ error: { code: -326xx, message: ... } }"| MCPClient["MCP Client"]
        SDKFormatResult -->|"{ result: { content: [...], isError: true } }"| MCPClient
    end

Explanation of Updated Error Flow and Transformations:

Errors are consistently through a unified AppError system:

  1. Validation Errors (ERR_1xxx series)

    • Used for validation issues (e.g., MissingParameter, InvalidArgument)
    • Thrown by tool executors during parameter validation
    • Mapped to protocol-level McpErrors in executeToolAndHandleErrors
  2. Business Logic Errors (ERR_2xxx and higher)

    • Used for all business logic and application-specific errors
    • Include specific error codes
    • Returned as serialized CallToolResults with isError: true
Changes

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.

  1. 2d ago First seen · 57 lines · 615 tokens per session scan A cba4f12da133

Subscribe to this mod's changes

errors is a cursor rule published in the GitHub repository chriscarrollsmith/taskqueue-mcp (70 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 615 tokens. 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.