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/dwmkerr/claude-toolkitnpx agentmods add skills/dwmkerr/claude-toolkit/pdf-signWrote 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/dwmkerr/claude-toolkit/pdf-sign)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.01230 |
| Opus 5 | $0.00037 | $0.00615 |
| Sonnet 5 | $0.00015 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
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.
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
- Try text search first.
page.search_for("SIGNATURE:")— a digital PDF locates fields directly. - 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) - Place content relative to the found label rects (see recipe).
- Always render and visually verify each modified page before declaring done:
Read the PNG — misplaced marks are common on the first pass.page.get_pixmap(dpi=100).save("check.png")
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
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.
- 9d ago First seen · 105 lines · 75 tokens per session scan A ec703a4aeea9
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.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.