audit-prompt

audit-prompt is a command for Claude Code from Owl-Listener/ai-design-skills. It costs 13 tokens per session (504 once invoked), scanned A, original, MIT.

A command for reviewing an existing AI prompt for clarity, structure, constraints, examples, context use, and unusual cases.

In plain words
What is it for?
Use it to assess a prompt's structure and rules, check its examples and context, score its quality, and identify improvements.
Why use it?
It finds instructions that are unclear, conflicting, incomplete, or likely to fail in less obvious situations.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the prompt-architecture plugin — 7 skills, 3 commands shipped together

Good fit Use it to assess a prompt's structure and rules, check its examples and context, score its quality, and identify improvements.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/ai-design-skills/audit-prompt
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.

Clone the repo
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skills

Made for: Claude Code.

Or install prompt-architecture, the plugin that ships this one along with the rest of its 7 skills, 3 commands.

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 audit-prompt

README.md
[![agentmods](https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/audit-prompt/github.svg)](https://agentmods.dev/commands/owl-listener/ai-design-skills/audit-prompt)
Your own site
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/audit-prompt"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/audit-prompt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-prompt

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/audit-prompt"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/audit-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00013 $0.00504
Opus 5 $0.00006 $0.00252
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00001 $0.00050

Measured 11d ago against content hash 1ba744e5c587, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-prompt 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 11d 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.

claude-plugin/prompt-architecture/commands/audit-prompt.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are auditing an existing prompt. Use only skills from the prompt-architecture plugin. Follow this process:

Step 1: Structural Analysis

Using system-prompt-structure:

  • Does the prompt have clear, separated sections?
  • Is identity/role defined clearly?
  • Are behavioral rules explicit and non-contradictory?
  • Are output specifications concrete?
  • Is the most important content at the beginning?
  • Score structure quality (1-5)

Step 2: Constraint Analysis

Using constraint-specification:

  • Are constraints specific and measurable?
  • Are there constraint conflicts?
  • Is there a clear priority hierarchy?
  • Are there missing constraints that should be added?
  • Score constraint quality (1-5)

Step 3: Example Analysis

Using few-shot-patterns:

  • Are there examples? Are there enough?
  • Do examples demonstrate the right behavior?
  • Are examples diverse and high-quality?
  • Do examples match the stated constraints?
  • Score example quality (1-5)

Step 4: Context Analysis

Using context-engineering:

  • Is the context budget well-allocated?
  • Is information ordered effectively?
  • Is there unnecessary content consuming context space?
  • Are context injection points well-designed?
  • Score context design quality (1-5)

Step 5: Edge Case Testing

Generate 5 challenging inputs and predict how the prompt would handle them:

  • An ambiguous request
  • A request at the boundary of the prompt's scope
  • A very simple request (is the prompt over-engineered for simple cases?)
  • A very complex request (does the prompt handle complexity?)
  • An adversarial or tricky request

Step 6: Versioning Assessment

Using prompt-versioning:

  • Is the prompt versioned and tracked?
  • Is there documentation for why it's written this way?
  • Are there test cases?
  • Is there a review process?

Output

Deliver a prompt audit report:

  1. Overall quality score (1-5) with justification
  2. Section-by-section analysis with scores
  3. Issues found: Issue | Severity | Category | Recommendation
  4. Edge case analysis with predicted behavior
  5. Top 5 improvements ranked by expected impact
  6. Rewritten prompt (improved version) if significant changes are needed

Read the full file on GitHub · 57 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. 11d ago First seen · 57 lines · 13 tokens per session scan A 1ba744e5c587

Subscribe to this mod's changes

audit-prompt is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 504 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.