Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ThierryN/fire-flownpx agentmods add skills/thierryn/fire-flow/pdf-forms-integrationWrote 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/thierryn/fire-flow/pdf-forms-integration)<a href="https://agentmods.dev/skills/thierryn/fire-flow/pdf-forms-integration"><img src="https://agentmods.dev/badge/skills/thierryn/fire-flow/pdf-forms-integration.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 | $0.00045 | $0.05063 |
| Opus 5 | $0.00023 | $0.02531 |
| Sonnet 5 | $0.00009 | $0.01013 |
| Haiku 4.5 | $0.00005 | $0.00506 |
Grade A, and why
pdf-forms-integration scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -o public/irs-forms/f656.pdf https://www.irs.gov/pub/irs-pdf/f656.pdf How it starts
The opening of the file, as written. The whole thing — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Forms Integration Skill
Purpose: Guide Claude in integrating official fillable PDF forms (especially GTA forms) into web applications
Use Cases:
- Integrating official GTA PDF forms (Form 656, 433-A, 433-B, etc.)
- Auto-populating AcroForm fields from user data
- Allowing users to manually edit PDFs in browser
- Downloading filled PDFs for submission
Key Technologies: pdf-lib, PDF.js, React, TypeScript
Overview
This skill helps integrate official PDF forms (with AcroForm fields) into web applications, enabling:
- Loading official PDFs from GTA or other sources
- Auto-populating form fields programmatically
- Allowing users to edit fields directly in the PDF
- Downloading the completed PDF
Core Concepts
AcroForm Fields
- What: Interactive form fields embedded in PDFs
- Types: Text fields, checkboxes, radio buttons, dropdowns
- Field Names: Cryptic identifiers like
topmostSubform[0].Page1[0].f1_01[0] - Browser Support: Chrome, Firefox, Edge, Safari all support editing AcroForms
pdf-lib Library
- Best For: Programmatic PDF manipulation (filling fields, generating PDFs)
- NOT For: Interactive editing in browser (use native browser support)
- Use Cases: Pre-filling PDFs, batch processing, server-side generation
PDF.js Library
- Best For: Rendering PDFs in browser
- Limitations: Not designed for form filling (use pdf-lib or native browser)
- Use Case: Custom PDF viewer, annotation tools
Implementation Strategy
Recommended Approach: Hybrid System
Step 1: Use pdf-lib to pre-fill fields from auto-populate Step 2: Display filled PDF in iframe using native browser PDF viewer Step 3: Let users edit directly in PDF (native browser support) Step 4: Users download the edited PDF
Why This Works:
- ✅ Pre-filling is fast (pdf-lib)
- ✅ Editing is native (no custom UI needed)
- ✅ Works offline (PDFs cached locally)
- ✅ Legally compliant (official GTA forms)
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.
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.
- 3d ago First seen · 663 lines · 45 tokens per session scan A 4a0c13911d92
pdf-forms-integration is a skill published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 25d ago), licensed MIT. It adds 45 tokens to every session and 5,063 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Work with PDF files using the environment's built-in PDF and document tools. Use when the user wants to inspect, summarize, split, merge, compress, or convert PDFs.
pdftomarkdown
Converts PDF documents, Word files (.docx), CSV spreadsheets, and YouTube video URLs into clean, token-efficient Markdown with smart table and heading structure detection.
nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.
visa-doc-translate
Translate visa application documents (images) to English and create a bilingual PDF with original and translation.
PDF files: create, read, merge, fill, OCR, edit text.
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…