prompt-refactor

prompt-refactor is a skill for Claude Code, Codex from microsoft/hve-core. It costs 25 tokens per session (458 once invoked), scanned A, original, MIT.

A compatibility route for cleaning up existing prompt-engineering files while preserving their behavior. It sends the work through the broader HVE Builder refactoring process.

In plain words
What is it for?
Use it to simplify approved prompts or other instruction artifacts, preserve specified behavior, and receive static-review, behavior-test, and validation results.
Why use it?
Older workflows may still refer to prompt-refactor even though the main refactoring process has moved elsewhere. This keeps those requests working while applying review, testing, and host checks.

Skill for Claude CodeCodex

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 skills/microsoft/hve-core/prompt-refactor
Any agent
npx skills add microsoft/hve-core --skill prompt-refactor
Clone the repo
git clone --depth 1 https://github.com/microsoft/hve-core

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-refactor

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/hve-core/prompt-refactor.svg)](https://agentmods.dev/skills/microsoft/hve-core/prompt-refactor)
Your own site
<a href="https://agentmods.dev/skills/microsoft/hve-core/prompt-refactor"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/prompt-refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 458 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 $0.00025 $0.00458
Opus 5 $0.00013 $0.00229
Sonnet 5 $0.00005 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 4d ago against content hash 4c9e534af56b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-refactor 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 4d 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.

.github/skills/hve-core/prompt-refactor/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Refactor Compatibility Skill

Goal

Preserve legacy prompt-refactor activation while simplifying approved prompt-engineering artifacts through the hve-builder refactor route and its independent quality gates.

Flow

  1. Translate promptFiles to existing targets and resolve the behavior that must remain unchanged.
  2. When requirements are omitted, use the HVE Builder baseline review to derive evidence-backed cleanup objectives.
  3. Activate hve-builder with mode=refactor, the approved write boundary, requirements, and any caller-owned evidence root.
  4. Return the HVE Builder static verdict, behavior-test fidelity and verdict, validation result, and overall outcome.

Inputs

  • promptFiles: existing prompt-engineering artifacts to refactor
  • requirements: optional cleanup objectives, constraints, and preserved behavior
  • evidenceRoot: optional caller-owned HVE Builder evidence path

Success Criteria

  • The approved targets are simpler without unintended behavior change.
  • Static review, behavior testing, and host validation pass.
  • Source changes stay inside the approved write boundary.
  • The returned overall outcome is unchanged from hve-builder.

Constraints

  • Do not dispatch retired named lifecycle workers.
  • Do not create a second orchestration loop or sandbox contract.
  • Route a requested type change, artifact split, or new support artifact back through HVE Builder scope approval.

Stop Rules

  • Stop Pass only when the HVE Builder refactor route passes every required gate.
  • Preserve Revise, Deferred, or Blocked and its rerun condition.
  • Ask when preserved behavior or write scope cannot be inferred safely.

Handoff

Use prompt-analyze for read-only follow-up review and prompt-builder when the requested work intentionally changes behavior or creates artifacts.

Final Response Contract

Return targets, changed files, refactor rationale, static verdict, behavior-test fidelity and verdict, validation result, overall outcome, evidence links, and next action.

Read the full file on GitHub · 54 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. 4d ago First seen · 54 lines · 25 tokens per session scan A 4c9e534af56b

Subscribe to this mod's changes

prompt-refactor is a skill published in the GitHub repository microsoft/hve-core (1,426 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 458 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens