Rt

F 50 completed
Cli Tool
unknown / go · tiny
40
Files
2,105
LOC
0
Frameworks
4
Languages

Pipeline State

completed
Run ID
#304108
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
34.77
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47332
Member of a group with 1 similar repo(s) — canonical #92402 view group →
Top concepts (1)
CLI Tool
Repobility · MCP-ready · https://repobility.com

AI Prompt

Build me a command-line interface (CLI) tool written in Go that acts as a token compressor for command outputs before they are sent to a Large Language Model (LLM). The tool should allow users to run arbitrary commands using `rt run <command>` and support listing available filters with `rt ls`. It needs to manage filters defined in TOML files, supporting built-in filters for common commands like `git status` and `docker compose`. Additionally, implement functionality to view filter details using `rt show <filter_name>` and track token savings with `rt gain`.
go cli command-line llm token-compression scripting git docker toml
Generated by gemma4:latest

Catalog Information

rt is a CLI tool that compresses the output of commands before it reaches a Large Language Model (LLM) context, reducing unnecessary tokens.

Description

rt intercepts the raw output of commands like git status, docker compose up, or npm test and reduces it to its essence. This is useful as a hook for LLM agents like Claude Code that execute terminal commands. When an LLM executes a command, the raw output consumes hundreds or thousands of unnecessary tokens: progress bars, hashes, blank lines, repetitive metadata. rt intercepts this output and compresses it.

الوصف

تستخدم rt لضغط الناتج من الأوامر قبل أن يصل إلى سياق نموذج اللغة الكبيرة، مما يقلل من التكلفة غير الضرورية للنقاط.

Novelty

7/10

Tags

command-compression large-language-models token-reduction terminal-output-processing

Claude Models

claude-opus-4.6

Quality Score

F
49.8/100
Structure
44
Code Quality
53
Documentation
38
Testing
0
Practices
80
Security
100
Dependencies
70

Strengths

  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No tests found \u2014 high risk of regressions
  • No CI/CD configuration \u2014 manual testing and deployment
  • 284 duplicate lines detected \u2014 consider DRY refactoring

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

4.6h
Tech Debt (D)
Medium
DORA Rating
A
OWASP (100%)
Repobility — the code-quality scanner for AI-generated software · https://repobility.com
FAIL
Quality Gate
A
Risk (17)
Unknown
License
3.9%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

go
62.1%
markdown
20.7%
toml
16.7%
shell
0.4%

Frameworks

None detected

Symbols

function52
struct14
variable2
constant1
method1
type_alias1

Concepts (1)

Source-of-truth: Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
auto_categoryCLI Toolcli60%

Quality Timeline

1 quality score recorded.

View File Metrics
Repobility analyzer · published findings · https://repobility.com

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/27936.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV