pdf-sign

pdf-sign is a skill for Claude Code from dwmkerr/claude-toolkit. It costs 75 tokens per session (1,230 once invoked), scanned A, original, MIT.

A tool for signing and completing PDF documents, including scanned forms that do not contain selectable text.

In plain words
What is it for?
Use it to sign letters, claim forms, and contracts, tick checkboxes, and fill in dates, names, and phone numbers.
Why use it?
It places a signature and form details in the document, using text search or optical character recognition when needed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 -m venv ./scratch/venv # or /tmp outside a repo.

Part of the dwmkerr plugin — 5 skills, 1 command shipped together

Good fit Use it to sign letters, claim forms, and contracts, tick checkboxes, and fill in dates, names, and phone numbers.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/dwmkerr/claude-toolkit
agentmods
npx agentmods add skills/dwmkerr/claude-toolkit/pdf-sign

Made for: Claude Code.

Or install dwmkerr, the plugin that ships this one along with the rest of its 5 skills, 1 command.

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 pdf-sign

README.md
[![agentmods](https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/pdf-sign/github.svg)](https://agentmods.dev/skills/dwmkerr/claude-toolkit/pdf-sign)
Your own site
<a href="https://agentmods.dev/skills/dwmkerr/claude-toolkit/pdf-sign"><img src="https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/pdf-sign/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 pdf-sign

Your own site · 80×15
<a href="https://agentmods.dev/skills/dwmkerr/claude-toolkit/pdf-sign"><img src="https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/pdf-sign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00075 $0.01230
Opus 5 $0.00037 $0.00615
Sonnet 5 $0.00015 $0.00246
Haiku 4.5 $0.00007 $0.00123

Measured 9d ago against content hash ec703a4aeea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pdf-sign 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 9d 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.

plugins/dwmkerr/skills/pdf-sign/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Sign

Sign and fill PDF forms programmatically. Works on both digital PDFs (with a text layer) and scanned PDFs (via OCR).

Signature image

Always ask the user where their signature image is — never assume a location, and never commit a signature image to a repository. A scanned signature (dark ink on white) works best.

If the image has a white background (typical JPG scan), convert it to a transparent PNG first — otherwise the overlay blanks out any text or lines beneath it:

from PIL import Image
img = Image.open(SRC_JPG).convert("RGBA")
img.putdata([(0, 0, 0, 0 if (r+g+b)//3 > 200 else 255-(r+g+b)//3)
             for r, g, b, a in img.getdata()])
img.save(OUT_PNG)

Save the transparent version next to the original so it can be reused.

Setup

pymupdf in a venv (system Python is often externally managed):

python3 -m venv ./scratch/venv   # or /tmp outside a repo
./scratch/venv/bin/pip install -q pymupdf pillow

OCR (scanned PDFs) needs tesseract: brew install tesseract, and set TESSDATA_PREFIX (Homebrew: /opt/homebrew/share/tessdata).

Approach

  1. Try text search first. page.search_for("SIGNATURE:") — a digital PDF locates fields directly.
  2. Scanned PDF → page.get_text() returns empty. Fall back to an OCR textpage:
    tp = page.get_textpage_ocr(full=True, dpi=200)
    hits = page.search_for("SIGNATURE:", textpage=tp)
    
  3. Place content relative to the found label rects (see recipe).
  4. Always render and visually verify each modified page before declaring done:
    page.get_pixmap(dpi=100).save("check.png")
    
    Read the PNG — misplaced marks are common on the first pass.

Recipe

import os
os.environ.setdefault("TESSDATA_PREFIX", "/opt/homebrew/share/tessdata")
import pymupdf

doc = pymupdf.open(SRC)
page = doc[0]
tp = page.get_textpage_ocr(full=True, dpi=200)  # omit for digital PDFs

def find(needle):
    hits = page.search_for(needle, textpage=tp)
    return hits[0] if hits else None

# Signature: transparent PNG spanning the line, right of the label
r = find("SIGNATURE:")
page.insert_image(pymupdf.Rect(r.x1 + 40, r.y0 - 32, r.x1 + 180, r.y1 + 4),
                  filename=SIGNATURE_PNG, keep_proportion=True)

# Text field: right of label, baseline-aligned
r = find("DATE:")
page.insert_text((r.x1 + 15, r.y1 - 2), "01/31/2026", fontsize=11, color=(0, 0, 0.55))

# Checkbox: box sits ~22pt left of its label text
r = find("Check here if your name")
page.insert_text((r.x0 - 22, r.y1 - 2), "X", fontsize=12, color=(0, 0, 0.55))

doc.save(OUT)  # never overwrite the source

Read the full file on GitHub · 105 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. 9d ago First seen · 105 lines · 75 tokens per session scan A ec703a4aeea9

Subscribe to this mod's changes

pdf-sign is a skill published in the GitHub repository dwmkerr/claude-toolkit (23 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,230 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories