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.
npx skills add ClicheFactory/clichefactory-mcp --skill openclawgit clone --depth 1 https://github.com/ClicheFactory/clichefactory-mcpWrote 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.
[](https://agentmods.dev/skills/clichefactory/clichefactory-mcp/openclaw)<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>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.
| Model | Per session | Once 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 |
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.
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 documentschema— JSON schema (inline object or path to a.jsonfile)mode—"service"(default, ClicheFactory cloud) or"local"(BYOK, advanced)extraction_mode— omit for default OCR+LLM, or"fast"for multimodal LLM without OCRmodel— 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 documentmode—"service"(default) or"local"
doctor
Checks configuration, Python dependencies, and system binaries. Call this when extraction fails to diagnose the issue.
Workflow
- If the user provides a document without a schema, call
to_markdownfirst to see the content. - Build a JSON schema from what you see (or from the user's description of what they need).
- Call
extractwith the file and schema (service mode is the default). - If extraction returns validation errors, inspect them — the schema may need adjustment (wrong types, missing fields, etc.).
- If extraction fails entirely, call
doctorto check whether the API key is configured.
Local mode (advanced)
For BYOK / on-machine extraction, install local extras and set LLM credentials:
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.
- 7d ago First seen · 103 lines · 32 tokens per session scan A cd3a0557ae03
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.
Other skills, from other repositories
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
markdown-converter
Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
unified-deliverable-workflow
Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery.
document-python-direct-exec
Use direct Python execution for reliable spreadsheet and document/PDF generation operations.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.