anonymize-prompt

anonymize-prompt is a skill for Claude Code, Codex from vthinkdeveloper/vthink-agent-toolkit. It costs 58 tokens per session (1,019 once invoked), scanned A, original, MIT.

A prompt-sanitising tool that rewrites a technical problem without private company, project, class, URL, or internal terminology.

In plain words
What is it for?
Use it to prepare a safer question for a search engine or external AI assistant. It can use the current conversation and an optional problem description.
Why use it?
It helps you seek outside help without accidentally revealing proprietary details while keeping the technical problem understandable.

Skill for Claude CodeCodex

Part of the vthink-agent-toolkit plugin — 12 skills, 1 command shipped together

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/vthinkdeveloper/vthink-agent-toolkit/anonymize-prompt
Any agent
npx skills add vthinkdeveloper/vthink-agent-toolkit --skill anonymize-prompt
Clone the repo
git clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkit

Made for: Claude Code, Codex.

Or install vthink-agent-toolkit, the plugin that ships this one along with the rest of its 12 skills, 1 command.

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 anonymize-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/vthinkdeveloper/vthink-agent-toolkit/anonymize-prompt.svg)](https://agentmods.dev/skills/vthinkdeveloper/vthink-agent-toolkit/anonymize-prompt)
Your own site
<a href="https://agentmods.dev/skills/vthinkdeveloper/vthink-agent-toolkit/anonymize-prompt"><img src="https://agentmods.dev/badge/skills/vthinkdeveloper/vthink-agent-toolkit/anonymize-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,019 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 $0.00058 $0.01019
Opus 5 $0.00029 $0.00509
Sonnet 5 $0.00012 $0.00204
Haiku 4.5 $0.00006 $0.00102

Measured 3d ago against content hash 6a7c3ddd2283, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anonymize-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 3d 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.

skills/anonymize-prompt/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anonymize Prompt

Generate a privacy-safe, anonymized prompt that the user can paste into external search engines and AI chatbots to get help — without exposing ANY proprietary details.

Inputs

  1. Conversation context — the current conversation where the problem is being discussed
  2. User's argument (optional) — a plain-text description of the problem passed as the skill argument

Workflow

Step 1: Understand the Problem

From the conversation context and user's argument, identify:

  • What is the core technical problem?
  • What technologies/frameworks are involved? (these are public knowledge — keep them)
  • What error messages or symptoms are observed?
  • What has been tried so far?

Step 2: Anonymize Everything Proprietary

Apply ALL of the following replacements systematically:

Category Example Before Example After
Company/product names AcmeCorp, my-service "our application", "the project"
Class names OrderManager, PaymentTracker DataManager, ProcessTracker
Variable/method names buildOrderInstance() buildDataStructure()
Package paths com.acme.app.apiImpl com.example.app.impl
Internal URLs localhost:8080/internal/api/v0 localhost:8080/app/api/v1
Database/table names acme_metadata, order_definitions app_metadata, entity_definitions
Internal jargon proprietary domain terms describe functionally in plain language
File paths /src/main/java/com/acme/... /src/main/java/com/example/...
Config keys acme.security.* app.security.*
Ticket IDs PROJ-1931 remove entirely
Branch names PROJ-1931-add-offline-access remove entirely
Colleague names any person names remove entirely
Docker/service names my-api, acme-web "the api service", "the web service"

Step 3: Preserve Technical Accuracy

Keep ALL of the following (they are public knowledge):

  • Framework names: Spring, Spring Security, Hibernate, React, Redux, Webpack, Maven, etc.
  • Library versions: Spring 5.x, Java 14, PostgreSQL 12, etc.
  • Standard patterns: OAuth2/OIDC, REST, JDBC, ACL, etc.
  • Error messages (but scrub any proprietary class/package names within them)
  • Stack trace structure (but anonymize class names)
  • Configuration property formats (but anonymize the property names)

Read the full file on GitHub · 102 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. 3d ago First seen · 102 lines · 58 tokens per session scan A 6a7c3ddd2283

Subscribe to this mod's changes

anonymize-prompt is a skill published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,019 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

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-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

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

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

Emily2040/seedance-2.0 · 48 tokens