Kiro Usage Telemetry Analysis

VerifiedSafe

Analyzes Kiro IDE telemetry data, including credit usage, tokens, and chat histories from local SQLite databases on Windows.

Sby Skills Guide Bot
Data & AIIntermediate
7/26/2026
Claude Code
#kiro#telemetry#token-usage#credit-limits#chat-logs

Recommended for

Automated summary

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
When to use it

Use when you need to audit Kiro IDE usage, check token consumption, or identify recurring tool errors.

When not to use it

Do not use if you need cross-platform support or if the Kiro installation path differs from the default Windows location.

Security analysis

Safe
Quality score90/100

The 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

How this analysis is made

Examples

Check current credit usage
Run the analyze_credits script to show my used and available Kiro credits and total lifetime tokens.
Analyze chat history for errors
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:

  1. Credit Usage & Tokens: Pull lifetime token counts from Kiro's internal tracking DB and compare them against the user's allocated monthly invocations.
  2. Chat & Session Analysis: Count bot vs human interactions and map out failed operations (such as webFetch limits or tool invocation errors) from the JSON-encoded chat histories.
  3. 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:

  1. To retrieve credit and token metrics: Run the analyze_credits.py script.

    python scripts/analyze_credits.py
    

    This 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.

  2. To retrieve chat history and identify tool failures: Run the parse_chats.py script.

    python scripts/parse_chats.py
    

    This 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 a tool action 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]\

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/kiro-usage-telemetry-analysis-ms1aw4q5/download' --output '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md.part' && mv '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md.part' '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md' && test -s '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/kiro-usage-telemetry' && cp -R '.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5' '.claude/skills/kiro-usage-telemetry'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5'

openskills read 'kiro-usage-telemetry-analysis-ms1aw4q5'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/kiro-usage-telemetry-analysis-ms1aw4q5/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills