Sparn

B 81 completed
Other
cli / typescript · small
147
Files
24,298
LOC
2
Frameworks
6
Languages

Pipeline State

completed
Run ID
#389567
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
56.40
Framework unique
Isolation
Last stage change
2026-05-10 03:35:02
Deduplication group #49364
Member of a group with 16 similar repo(s) — canonical #81878 view group →
Top concepts (2)
Project DescriptionWeb Frontend
Want this analysis on your repo? https://repobility.com/scan/

AI Prompt

Create a command-line tool called Sparn designed to optimize context for AI coding agents like Claude Code. The tool should allow users to compress verbose tool outputs from commands like `git log` or `npm test` using a relay function. I also need functionality to analyze the codebase structure to generate a dependency graph, search files using FTS5, and automatically generate a `CLAUDE.md` file summarizing the project. Finally, include options to run a background daemon for continuous optimization.
typescript cli ai-coding-agent context-optimization command-line-tool
Generated by gemma4:latest

Catalog Information

Context optimization for AI coding agents. Reduces token usage by 60-90% so your Claude Code sessions last longer and cost less.

Description

Context optimization for AI coding agents. Reduces token usage by 60-90% so your Claude Code sessions last longer and cost less.

Novelty

3/10

Tags

typescript cli ai-coding-agent context-optimization command-line-tool

Technologies

react zod

Claude Models

claude-opus-4-6

Quality Score

B
81.2/100
Structure
88
Code Quality
70
Documentation
89
Testing
85
Practices
67
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (65% test-to-source ratio)
  • Code linting configured (biome)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Weaknesses

  • 1346 duplicate lines detected \u2014 consider DRY refactoring
  • 1 'god files' with >500 LOC need decomposition

Security & Health

6.1h
Tech Debt (A)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Source: Repobility analyzer · https://repobility.com
MIT
License
4.1%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

typescript
68.6%
json
22.1%
markdown
6.9%
javascript
1.8%
yaml
0.5%
text
0.1%

Frameworks

React Vitest

Concepts (2)

Scored by Repobility's multi-pass pipeline · https://repobility.com
CategoryNameDescriptionConfidence
Repobility (the analyzer behind this table) · https://repobility.com
auto_descriptionProject DescriptionContext optimization for AI coding agents. Reduces token usage by 60-90% so your Claude Code sessions last longer and cost less.80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/113882.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV