read-text

read-text is a skill for Claude Code, Codex from Borda/vision-delivery. It costs 143 tokens per session (1,078 once invoked), scanned A, original, Apache-2.0.

An image-text extraction workflow for reading specific fields such as numbers, labels, codes, and document entries. It checks results against independently transcribed examples.

In plain words
What is it for?
Use it to read serial, part, date, or lot numbers; license plates; meters and gauges; barcodes and QR codes; invoices; forms; and other text in images.
Why use it?
It separates finding text from decoding and validating it, making it easier to identify why a scanned value is wrong.

Skill for Claude CodeCodex

Part of the sentinel plugin — 13 skills, 2 agents, 1 hook, 1 MCP server 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/borda/vision-delivery/read-text
Any agent
npx skills add Borda/vision-delivery --skill read-text
Clone the repo
git clone --depth 1 https://github.com/Borda/vision-delivery

Made for: Claude Code, Codex.

Or install sentinel, the plugin that ships this one along with the rest of its 13 skills, 2 agents, 1 hook, 1 MCP server.

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 read-text

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/vision-delivery/read-text.svg)](https://agentmods.dev/skills/borda/vision-delivery/read-text)
Your own site
<a href="https://agentmods.dev/skills/borda/vision-delivery/read-text"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/read-text.svg" alt="Measured on agentmods" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,078 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 $0.00143 $0.01078
Opus 5 $0.00072 $0.00539
Sonnet 5 $0.00029 $0.00216
Haiku 4.5 $0.00014 $0.00108

Measured 5d ago against content hash 32bc07321f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

read-text 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 5d 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-skills/read-text/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract the exact fields needed by the business process and clear an independently transcribed acceptance set. Separate region localization, text decoding, normalization, and field validation so failures have an owner.

Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific capability, dataset, training, inference, workflow, or deployment action. Use installed official Roboflow skills or current MCP resources only for read-only discovery and sourced action-brief inputs; never invoke provider execution. Do not preserve current engine names, blocks, IDs, or invocation syntax here.

Follow ../../resources/fde-methodology.md; apply these text-specific rules.

1. Define fields and operational action

Inspect representative images, existing schemas, expected formats, code, and error handling. Ask at most three missing questions:

  • Which exact fields must be returned, and what action uses them?
  • Are substitutions allowed, or must the whole field match exactly?
  • Which capture conditions and scripts/languages occur in production?

Freeze before selecting or tuning a candidate:

Acceptance ID: <session/revision>
Business decision: <action enabled by extracted fields>
Gold set: <independent transcription source, split, adjudicator>
Primary metric and threshold: <exact field match/CER/valid-code rate>
Secondary guardrails: <critical-field recall, rejection rate, latency>
Frozen before baseline: <timestamp and confirmation>
Baseline result (diagnostic only): <not run yet>

2. Freeze the extraction schema

For each field, record name, type, allowed alphabet, normalization, format/checksum rule, null behavior, confidence/review policy, and whether localization is needed. Preserve raw text separately from normalized output. Never silently “correct” a value unless the correction rule was frozen and both forms are retained.

3. Select and evaluate candidates

Read the full file on GitHub · 94 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. 5d ago First seen · 94 lines · 143 tokens per session scan A 32bc07321f33

Subscribe to this mod's changes

read-text is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 25d ago), licensed Apache-2.0. It adds 143 tokens to every session and 1,078 once invoked, about $0.0007 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

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

validate

Run the profile-aware DocFlow documentation readiness gate. Always blocks broken links, stale maps, and missing headings; applies native naming and section rules strictly to new scaffolds while treating established adopted structures as cleanup guidance.

MedAdemBHA/docflow · 44 tokens

doctor

Read-only docflow diagnosis: scans docs, config, changelog, and links, then recommends init, adopt, or repair. Use when asked "check docs setup", "should I set up docflow", "why is docflow not working", or "doctor".

MedAdemBHA/docflow · 56 tokens

repair

Safe maintenance for an existing docflow setup. Regenerates INDEX.md, installs or refreshes recognized DocFlow-managed helper scripts, runs link checks, and reports placeholder/validation issues. Use when docflow exists, after adding or renaming docs, or when doctor recommends repair.

MedAdemBHA/docflow · 58 tokens

pipeline

Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…

kardebadas/claude-plugin · 80 tokens

craft

Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…

kardebadas/claude-plugin · 83 tokens