Our review
Analyzes Kiro AI IDE telemetry data from local SQLite databases and logs to report token usage, credit limits, and chat history.
Strengths
- Automates extraction of usage metrics from local Kiro databases
- Identifies tool failures and errors in chat logs
- Provides clear warnings when credit usage exceeds 80%
Limitations
- Only works on Windows due to reliance on %APPDATA% paths
- Requires Python environment to execute the supplied scripts
- Does not support real-time monitoring or historical trends beyond current data
Use when you need to audit Kiro IDE usage, check token consumption, or identify recurring tool errors.
Do not use if you need cross-platform support or if the Kiro installation path differs from the default Windows location.
Security analysis
SafeThe skill only reads local telemetry data files (SQLite, chat logs) in the user's own AppData directory using Python scripts. There is no network activity, no destructive commands, no exfiltration, and no obfuscated payloads. The instructions are transparent and limited to analysis.
No concerns found
Examples
Run the analyze_credits script to show my used and available Kiro credits and total lifetime tokens.Run the parse_chats script to summarize my Kiro chat history and list any tool failures or errors.name: kiro-usage-telemetry description: Analyzes and reports Kiro AI IDE telemetry data, token usage, credit limits, and chat logs from local SQLite databases and log directories on Windows. license: MIT metadata: author: User version: "1.0"
Kiro Usage Telemetry Skill
This skill enables an AI Agent to extract, analyze, and report telemetry data generated by the Kiro IDE. It parses local data storage (SQLite databases, .chat history records, and session logs) which reside in the Windows %APPDATA%\Kiro directory.
Capabilities
By utilizing the predefined scripts bundled in the scripts/ directory, you can inspect:
- Credit Usage & Tokens: Pull lifetime token counts from Kiro's internal tracking DB and compare them against the user's allocated monthly invocations.
- Chat & Session Analysis: Count bot vs human interactions and map out failed operations (such as
webFetchlimits or tool invocation errors) from the JSON-encoded chat histories. - Log Traversal: Review application events from the
logs/directory.
Instructions for Agents
When a user asks to inspect their Kiro telemetry, logs, or credit usage, follow these steps:
-
To retrieve credit and token metrics: Run the
analyze_credits.pyscript.python scripts/analyze_credits.pyThis will output the current used vs available credits (evaluated in "INVOCATIONS") and the total lifetime prompt tokens (from
devdata.sqlite). If the percentage used is over 80%, explicitly warn the user. -
To retrieve chat history and identify tool failures: Run the
parse_chats.pyscript.python scripts/parse_chats.pyThis script parses all 32-character hexadecimal session folders stored in
%APPDATA%\Kiro\User\globalStorage\kiro.kiroagent\. It provides a summary of messages and isolates occurrences where Kiro attempted atoolaction but encountered an "Error" state. Highlight any of these failures to the user.
Data Locations Reference
If you need to query custom data manually, be aware of these Windows path structures:
- Global State (Credits):
%APPDATA%\Kiro\User\globalStorage\state.vscdb - Tokens Dataset:
%APPDATA%\Kiro\User\globalStorage\kiro.kiroagent\dev_data\devdata.sqlite - Chat JSON Histories:
%APPDATA%\Kiro\User\globalStorage\kiro.kiroagent\[session-hash]\*.chat - Session Logs:
%APPDATA%\Kiro\logs\[session-timestamp]\
Prompt Engineering
Data & AI
Prompt engineering best practices and templates to maximize AI outputs.
Data Visualization
Data & AI
Generates data visualizations and charts tailored to your data.
RAG Architecture Setup
Data & AI
Setup guide for RAG (Retrieval-Augmented Generation) architectures.