image-to-markdown-vp

image-to-markdown-vp is a skill for Codex from VectorPeak/vectorpeak-agent-skills. It costs 54 tokens per session (3,489 once invoked), scanned A, original, Apache-2.0.

A workflow for converting screenshots into structured, Obsidian-ready Markdown. It preserves visible headings, tables, formulas, diagrams, charts, and code as accurately as practical.

In plain words
What is it for?
Use it to process screenshots, reconstruct document structure, convert diagrams to Mermaid when appropriate, add alt text, and validate that visual regions are represented in the final Markdown.
Why use it?
It helps turn visual notes or interface captures into editable text without losing their layout or important structure. OCR means extracting text from an image.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents.

Good fit Use it to process screenshots, reconstruct document structure, convert diagrams to Mermaid when appropriate, add alt text, and validate that visual regions are represented in the final Markdown.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp
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.

Any agent
npx skills add VectorPeak/vectorpeak-agent-skills --skill image-to-markdown-vp
Clone the repo
git clone --depth 1 https://github.com/VectorPeak/vectorpeak-agent-skills

Made for: 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 image-to-markdown-vp

README.md
[![agentmods](https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp/github.svg)](https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp)
Your own site
<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp/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 image-to-markdown-vp

Your own site · 80×15
<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/image-to-markdown-vp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,489 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 $0.00054 $0.03489
Opus 5 $0.00027 $0.01744
Sonnet 5 $0.00011 $0.00698
Haiku 4.5 $0.00005 $0.00349

Measured 8d ago against content hash 37dd7e95ecd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

image-to-markdown-vp 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 8d 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.

knowledge-skills/image-to-markdown-vp/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image To Markdown VP

Purpose

Convert one or more screenshots into human-readable Obsidian-ready Markdown while preserving the visible structure as faithfully as practical.

This skill is for capture and reconstruction, not for rewriting or summarizing, unless the user explicitly asks.

Execution Mode

This skill defaults to multi-agent execution for real screenshot-to-Markdown work.

  • MUST use multi-agent execution whenever the task includes multiple screenshots, mixed region types, diagrams, charts, UI evidence, or continuation batches.
  • MUST assign one dedicated screenshot-handling agent. This agent owns screenshot inspection, crop decisions, remote uploads, alt text, and insertion anchors.
  • MUST assign one structure-reconstruction agent. This agent owns OCR hierarchy, tables, formulas, code fences, and Mermaid conversion.
  • The main agent owns merge, final write, and final validation.
  • If the batch is large, dense, or risky, add a validator agent to reconcile the region manifest against the final Markdown.
  • Only skip multi-agent execution when the task is truly tiny: one small screenshot with plain prose or a simple code block and no meaningful visual evidence.

Required Inputs

Before writing a file, the user must explicitly provide:

  • Output directory path
  • Output Markdown filename, or an unambiguous Markdown basename. If the basename is clear but .md is missing, append .md automatically.
  • One or more screenshots or images
  • A generation signal such as “生成”, “继续补充”, “输出到文件”, or equivalent

If the path or filename is missing, stop and ask. Do not invent the destination.

Multi-Batch Handling

  • Treat newly provided screenshots as part of the same capture set when the user clearly says they are continuing the same document.
  • Preserve screenshot order by conversation order and attachment order unless the user corrects it.
  • If the user says more images are coming, the final response MUST explicitly say the Markdown is still partial.
  • If the user adds more images after a file already exists, update the same file only when they explicitly ask to continue that file.
  • If a batch starts or ends in the middle of a section, table, formula, or code block, preserve only the visible content and do not invent the hidden continuation.

Read the full file on GitHub · 310 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 310 lines · 54 tokens per session scan A 37dd7e95ecd4

Subscribe to this mod's changes

image-to-markdown-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 3,489 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

okf

Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…

scaccogatto/okf-skills · 127 tokens

preprep

A Korean-language presentation-preparation workflow that develops a topic through questions, proposes several story structures, and keeps slides, speaker notes, scripts, and related documents aligned.

chrono-meta/forge-harness · 216 tokens

mxMigrateToDb

Use when the user says "/mxMigrateToDb", "migrate to db", "migrate local docs to mcp", "sync local docs", "import docs to knowledge db", "--extract-backlog", "extract legacy backlog", or otherwise wants to import local docs/.md fallback files into the MCP Knowledge-DB. Runs after MCP outages (when offline-fallback…

MicrotronX/mxLore · 126 tokens

typescript-providers

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

ComposioHQ/composio · 70 tokens

memstack-business-scope-of-work

Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.

cwinvestments/memstack · 70 tokens

validate

Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.

scaccogatto/okf-skills · 82 tokens