enhance

A command that turns a vague request into a clearer, structured prompt using selected guidance and reasoning steps. It shows the revised prompt and waits for approval before work begins.

In plain words
What is it for?
Use it to improve a request, or use clarification mode when you only want a few targeted questions to unblock the task.
Why use it?
It helps expose missing details and unclear goals before implementation starts.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/adilkalam/orca/enhance
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,036 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.04036
Opus 5 $0.00015 $0.02018
Sonnet 5 $0.00006 $0.00807
Haiku 4.5 $0.00003 $0.00404

Measured 2d ago against content hash d5529886086c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

enhance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/enhance.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STOP! This is the /enhance command - Enhancement Only!

YOUR SOLE PURPOSE: Transform the user's request into an enhanced prompt, then seek approval.

YOU MUST:

  1. Follow the enhancement process below
  2. Present the enhanced prompt clearly
  3. Ask for user approval before any execution

YOU MUST NOT:

  1. Start executing immediately
  2. Create implementation todos before approval
  3. Jump to fixing/implementing without permission

Original Request to Enhance: $ARGUMENTS

Check for Debug Mode

If $ARGUMENTS starts with "--debug", enable verbose mode:

  • Remove "--debug" from $ARGUMENTS before processing
  • Set DEBUG_MODE = true
  • Show all analysis steps and reasoning Otherwise:
  • Set DEBUG_MODE = false
  • Provide compact, focused output

Clarify Mode (--clarify)

If $ARGUMENTS starts with "--clarify":

  • Remove "--clarify" from $ARGUMENTS before processing
  • Goal: Ask 2–3 targeted questions to unblock the task, then stop
  • Produce ONLY:
    • A single AskUserQuestion with up to 3 crisp, non-overlapping questions
    • After answers, return a 3–5 line summary and 3 acceptance criteria
  • Do NOT generate a full enhanced prompt or orchestration plan in this mode
  • Suggest: "Run /enhance again without --clarify to generate the final enhanced prompt"

Phase 1: Context Analysis & Intelligence Gathering

If DEBUG_MODE, tell the user: " Debug mode enabled. Showing detailed analysis..." Otherwise, tell the user: " Enhancing your request..."

Handle Empty Arguments

If $ARGUMENTS is empty or just whitespace:

  • Ask the user to provide a request with examples
  • DO NOT guess from conversation history
  • Show examples: /enhance fix bug, /enhance implement feature X

Analyze Request Context

Understand the request by identifying:

  • What's being changed: Code, configuration, documentation, infrastructure
  • Risk level: Production impact, data handling, security implications
  • Scope: Single line fix vs architectural change
  • Technology context: Language, framework, available tools
  • Project size: Consider actual codebase size and complexity for realistic goals

Read the full file on GitHub · 428 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 428 lines · 0 tokens per session scan A d5529886086c

Subscribe to this mod's changes

enhance is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 4,036 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.