fela@agents:~$ @im "Fix login bug"

Prompt compiler for AI coding agents

One-Click Improve

Install a prompt layer that understands the agent surface before the agent starts work. @im and /im route rough requests through embedded skills, harness rules, and validation patterns so Codex, Claude Code, Cursor, and VS Code receive execution-ready tasks.

root@one-click-improve: ~/install

curl -fsSL https://improv.sh/install.sh | bash

install compare

same prompt, different outcome

Stop paying agents to rediscover the task.

The value is not prettier wording. It is whether the first model turn receives scope, harness context, acceptance criteria, and validation instead of a vague request.

raw prompt ~1.5k-6k tokens burned

2-4 clarification turns before the agent has enough scope to start useful implementation.

with one-click improve ~200-700 prep tokens

The task is compiled up front with harness, context, acceptance criteria, and validation.

estimated savings ~1.3k-5.3k tokens

For this rough `Fix login bug` request, before counting avoided rework and wrong-file edits.

without one-click improve

user: Fix login bug

agent first response:
- Which login flow is broken?
- What error do you see?
- What files should I inspect?
- Should I add tests?

cost:
The session starts with discovery. The agent has no target flow, no done condition, no validation plan, and no surface-specific instructions.

token burn estimate:
~1.5k-6k tokens before useful work.

with one-click improve

user: @im Fix login bug

one-click output:
## Objective
Fix the login bug in the affected auth flow.

## Harness
Use the active route for this surface: VS Code @im, Cursor /im, terminal @im, Claude Code /im, or Codex-ready copy.

## Context
Use the selected workspace, current editor/chat surface, and bundled improve-prompt skill. Confirm the failing login path before editing.

## Constraints
- Preserve auth API and session behavior unless the bug requires a focused change.
- Avoid unrelated account or UI refactors.

## Deliverables
- Code fix.
- Tests for the failing login path.
- Validation notes for valid and invalid credentials.

## Acceptance Criteria
- Login succeeds for the affected flow.
- Existing logout/session behavior does not regress.
- The edge case is covered by a test.

## Validation
Run targeted auth tests and record the manual login check.

token burn estimate:
~200-700 prep tokens before useful work.

agent-prep loop

What happens before your agent sees the prompt

One-Click Improve compiles intent into a task envelope: command route, context, constraints, deliverables, acceptance criteria, and validation.

$ invoke

Start from the panel, a selection, VS Code @im, Cursor /im, Claude Code /im, or terminal @im.

$ inspect

Detect missing scope, files, constraints, tests, ambiguity, architecture notes, and done conditions.

$ compile

Load the bundled skill and rewrite the request into an executable engineering task.

$ route

Send or copy the result in the command style that fits the current harness.

agent operating layer

A prompt compiler and harness router, not a thesaurus.

One-Click Improve sits between your intent and the model. It normalizes a rough ask into the exact shape each harness can execute: command syntax, missing context, constraints, deliverables, acceptance criteria, validation steps, and guardrails. The goal is higher yield from the same model call, with fewer correction loops.

surface awareness Understands whether the prompt is headed to VS Code Chat, Cursor, Claude Code, Codex, or a shell workflow.

skill execution Uses the bundled improve-prompt skill as the source of truth for structure and task discipline.

harness routing Maps one source skill into .claude, .cursor, .agents, and .github style command surfaces.

waste control Turns missing context into explicit questions or assumptions before tokens are spent on guesswork.

works where prompts start

Command routes for each environment

The same prompt-improvement engine is exposed through the shortcuts developers already reach for.

VS Code

Use the sidebar panel, improve selected text, or mention @im before a chat request.

@im Fix login bug

Cursor

Use the reliable slash command route for Cursor Chat and Cursor Agent workflows.

/im Add tests for session timeout

Terminal

Generate an improved prompt from any shell, then paste or pipe it into Claude Code or Codex.

@im "Refactor dashboard loading"

Harness Router

Ask which route and skill profile best fit the work before sending the task to an agent.

@harness "auth tests in Cursor"

before and after

The output is designed for execution

The improved prompt is not an essay. It is a work order with objective, context, constraints, deliverables, acceptance criteria, and validation steps.

Rough prompt

Fix login bug

Improved prompt

no key required

Works offline. Best with your key.

The local provider ships ready to use and now detects request type, domain, harness, safety, accessibility, and validation signals before it writes the task. Add your OpenAI, Anthropic, or OpenAI-compatible key when you want the strongest model-backed rewrite.

localNo network, smarter offline output

openaiSkill-guided model rewrite

anthropicClaude API rewrite

compatibleOpenRouter, Groq, Mistral, DeepSeek, Gemini, xAI

start here

Install once, improve prompts everywhere

The installer detects VS Code and Cursor, installs the extension, creates terminal shortcuts, writes Cursor and Claude command files, syncs the bundled skill to user-level harness folders, then optionally asks for a terminal provider key. You can skip it.

curl -fsSL https://improv.sh/install.sh | bash