prompt-analyze

prompt-analyze is a skill for Claude Code from microsoft/hve-core. It costs 25 tokens per session (497 once invoked), scanned A, original, MIT.

A read-only review helper for prompt, instruction, agent, skill, reference, or template files that sends analysis to a newer prompt-building process.

In plain words
What is it for?
Use it to review prompt files, test their behavior when requested, validate specific requirements, and receive findings and report links.
Why use it?
It checks prompt artifacts without changing their source and reports separate evidence about their wording and behavior.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

About the project

HVE Core is a collection of agents, prompts, coding instructions, and skills for building repeatable software-development workflows with GitHub Copilot. It is intended for individuals and teams that want structured AI-assisted research, planning, implementation, and review, while the catalogue entries provide many of its reusable workflow components.

microsoft/hve-core · 1,436 stars · on GitHub

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

Made for: Claude Code.

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-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/hve-core/prompt-analyze.svg)](https://agentmods.dev/skills/microsoft/hve-core/prompt-analyze)
Your own site
<a href="https://agentmods.dev/skills/microsoft/hve-core/prompt-analyze"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/prompt-analyze.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 497 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 5.1 $0.00025 $0.00497
Opus 5 $0.00013 $0.00249
Sonnet 5 $0.00005 $0.00099
Haiku 4.5 $0.00003 $0.00050

Measured 6d ago against content hash 7ca3e0138a75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prompt-analyze 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 6d 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-analyze/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Analyze Compatibility Skill

Goal

Preserve legacy prompt-analyze activation while producing independent static and behavior evidence through hve-builder in read-only review mode.

Flow

  1. Translate promptFiles to targets and infer current open or attached prompt-engineering artifacts when omitted.
  2. Activate hve-builder with mode=review, the targets, analysis requirements, requested behavior-test fidelity, and any caller-owned evidence root.
  3. Keep source artifacts read-only. Permit only review, behavior-test, and requested validation evidence writes.
  4. Return the static verdict, behavior-test fidelity and verdict, validation as Not requested unless the caller requested it, overall outcome, findings summary, and report links.

Inputs

  • promptFiles: existing prompt, instruction, agent, subagent, skill, reference, or template files to review
  • requirements: optional purpose, criteria, or behavior to emphasize
  • fidelity: optional simulation or native request, subject to HVE Builder Tester safety preconditions
  • evidenceRoot: optional caller-owned HVE Builder evidence path

Success Criteria

  • Source artifacts are unchanged.
  • Static review and required behavior testing complete or carry an explicit deferral.
  • Findings use the HVE rubric severity and fidelity contracts.
  • The response links the durable review and behavior reports.

Constraints

  • Do not dispatch retired named lifecycle workers.
  • Do not research, fix, refactor, or create source artifacts in this mode.
  • Do not describe simulation as native runtime evidence.

Stop Rules

  • Stop Pass when hve-builder review mode returns Pass.
  • Preserve Revise, Deferred, or Blocked and its rerun condition.
  • Stop before any source edit.

Handoff

Recommend prompt-builder for approved improvements or prompt-refactor for behavior-preserving cleanup. Both route changes through hve-builder.

Final Response Contract

Return targets, static verdict, behavior-test profile and fidelity, behavior verdict, validation result (Not requested unless requested), overall outcome, top findings, report links, and next action.

Read the full file on GitHub · 55 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. 6d ago First seen · 55 lines · 25 tokens per session scan A 7ca3e0138a75

Subscribe to this mod's changes

prompt-analyze is a skill published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 497 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

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.

Emily2040/seedance-2.0 · 61 tokens

omh-model-optimization

This is a Hermes-native model-optimization workflow skill.

rlaope/oh-my-hermes · 82 tokens