By doit2urself
Silently enhances prompt clarity by delegating PE evaluation to Claude via additionalContext injection
Claude Code plugin that silently evaluates prompt clarity and asks focused clarifying questions when needed.
PromptLens hooks into every UserPromptSubmit event and injects a lightweight coding-focused evaluation checklist (~400 tokens) via additionalContext. Claude uses this checklist to decide whether to proceed immediately or ask 1-2 clarifying questions before starting work.
You won't see the plugin working — it's designed to be invisible. Claude just becomes better at catching ambiguous requests.
claude plugin add /path/to/prompt-lens-plugin
Or clone and add:
git clone https://github.com/doit2urself/prompt-lens-plugin.git
claude plugin add ./prompt-lens-plugin
PromptLens automatically skips evaluation for prompts that don't benefit from it:
| # | Condition | Example |
|---|---|---|
| 1 | Empty / whitespace | "", " " |
| 2 | Slash commands | /help, /commit |
| 3 | Short hash memos | # note to self |
| 4 | Confirmations | y, ok, 네, go ahead |
| 5 | Selections | 1, first, 두 번째 |
| 6 | Standalone file paths | main.py, ./src/utils.ts |
| 7 | Code/error pastes (>=70% code lines) | Pure code blocks, tracebacks |
| 8 | Long prompts (>2000 chars) | Already well-specified |
Prefix any prompt with * to skip evaluation:
* just do it without checking
Set the environment variable to enable logging:
export PROMPTLENS_DEBUG=1
Logs go to promptlens.log in the plugin root and stderr.
python3 -m pytest tests/ -v
MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub doit2urself/prompt-lens-plugin --plugin prompt-lensUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses