# severity1/claude-code-prompt-improver

Intelligent prompt improver hook for Claude Code. Type vibes, ship precision.

Repository: https://github.com/severity1/claude-code-prompt-improver
Canonical: https://ross.abutalabs.com/products/claude-code-prompt-improver
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-03T11:40:44+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 87, longevity 22
- inputs: {"age_days": 319, "days_push": 91, "days_rel": 91, "gap_med": 7.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1916, forks 152 (observed 2026-08-28T04:05:53.922073+00:00)

## What it is
A Claude Code hook plugin that intelligently improves prompts at submit time, tool use, and subagent start, injecting contextual nudges so Claude produces better first outputs. It includes targeted nudges for clarity checks, plan mode, workflow guidance, output readability, and subagent routing.

## Use cases
- improve vague prompts before sending them to Claude Code
- reduce correction round-trips when coding with an AI agent
- automatically enter plan mode for complex multi-file tasks
- route research tasks to subagents with better context
- run long-running commands in the background with polling guidance

## When to choose
- you use Claude Code daily and want higher-quality first responses
- you want automatic clarification questions for vague requests
- you need structured plan-first workflows for non-trivial implementations

## When to avoid
- you don't use Claude Code or a compatible hook system
- you prefer fully manual control over every prompt you send
- you want a general-purpose prompt library outside an agentic coding workflow

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, agent-framework, developer-tools
- domain: developer-tools, large-language-models
- platform: python, cli
- tags: claude-code, hooks, prompt-optimization, subagent-routing, plan-mode, ai-agents, automation

## Member repositories
- severity1/claude-code-prompt-improver (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:53.922073+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:10:18.167149+00:00, confidence not recorded.
  - readme: https://github.com/severity1/claude-code-prompt-improver (fetched 2026-08-28T04:05:53.922073+00:00, sha 9b4a07dab06e)
- Data as of 2026-08-30T08:39:29.467469+00:00.