clichefactory

clichefactory is a skill for Claude Code, Codex from ClicheFactory/clichefactory-mcp. It costs 32 tokens per session (985 once invoked), scanned A, original, MIT.

A document-extraction tool that reads PDFs, images, Word files, spreadsheets, CSVs, and emails, then returns JSON matching a schema you provide.

In plain words
What is it for?
Use it to turn invoices, forms, reports, email files, or spreadsheets into structured JSON for later processing.
Why use it?
It removes the need to manually copy information from varied documents and check whether the result has the expected fields and format.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to turn invoices, forms, reports, email files, or spreadsheets into structured JSON for later processing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clichefactory/clichefactory-mcp/openclaw
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 ClicheFactory/clichefactory-mcp --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/ClicheFactory/clichefactory-mcp

Made for: Claude Code, 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 clichefactory

README.md
[![agentmods](https://agentmods.dev/badge/skills/clichefactory/clichefactory-mcp/openclaw.svg)](https://agentmods.dev/skills/clichefactory/clichefactory-mcp/openclaw)
Your own site
<a href="https://agentmods.dev/skills/clichefactory/clichefactory-mcp/openclaw"><img src="https://agentmods.dev/badge/skills/clichefactory/clichefactory-mcp/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 985 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 $0.00032 $0.00985
Opus 5 $0.00016 $0.00492
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 7d ago against content hash cd3a0557ae03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

clichefactory 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 7d 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.

integrations/openclaw/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClicheFactory — Structured Document Extraction

ClicheFactory extracts structured, Pydantic-validated data from documents. Give it a file and a JSON schema — it returns clean JSON.

This skill requires the clichefactory MCP server. Register it once:

openclaw mcp set clichefactory '{"command":"uvx","args":["clichefactory-mcp"],"env":{"CLICHEFACTORY_API_KEY":"cliche-your-key"}}'

Get your API key at clichefactory.com → Settings → API Keys. Free pages included, no credit card.

Verify with openclaw mcp list.

MCP Tools

extract

Primary tool. Takes a document file path and a JSON schema, returns structured JSON matching the schema.

Parameters:

  • file — absolute path to the document
  • schema — JSON schema (inline object or path to a .json file)
  • mode"service" (default, ClicheFactory cloud) or "local" (BYOK, advanced)
  • extraction_mode — omit for default OCR+LLM, or "fast" for multimodal LLM without OCR
  • model — LLM override, e.g. "openai/gpt-4o"

to_markdown

Converts a document to readable markdown. Use this to inspect contents before building a schema, or when extract fails and you need to understand the document structure.

Parameters:

  • file — absolute path to the document
  • mode"service" (default) or "local"

doctor

Checks configuration, Python dependencies, and system binaries. Call this when extraction fails to diagnose the issue.

Workflow

  1. If the user provides a document without a schema, call to_markdown first to see the content.
  2. Build a JSON schema from what you see (or from the user's description of what they need).
  3. Call extract with the file and schema (service mode is the default).
  4. If extraction returns validation errors, inspect them — the schema may need adjustment (wrong types, missing fields, etc.).
  5. If extraction fails entirely, call doctor to check whether the API key is configured.

Local mode (advanced)

For BYOK / on-machine extraction, install local extras and set LLM credentials:

Read the full file on GitHub · 103 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. 7d ago First seen · 103 lines · 32 tokens per session scan A cd3a0557ae03

Subscribe to this mod's changes

clichefactory is a skill published in the GitHub repository ClicheFactory/clichefactory-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 985 once invoked, about $0.0002 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.