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 agentmods add skills/getemboss-ai/emboss-claude-plugin/embossnpx skills add GetEmboss-ai/emboss-claude-plugin --skill embossgit clone --depth 1 https://github.com/GetEmboss-ai/emboss-claude-pluginWrote 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/getemboss-ai/emboss-claude-plugin/emboss)<a href="https://agentmods.dev/skills/getemboss-ai/emboss-claude-plugin/emboss"><img src="https://agentmods.dev/badge/skills/getemboss-ai/emboss-claude-plugin/emboss.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 | $0.00087 | $0.01287 |
| Opus 5 | $0.00044 | $0.00643 |
| Sonnet 5 | $0.00017 | $0.00257 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
emboss 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Emboss
Emboss turns flat PDF forms into fillable AcroForm PDFs and fills them from
values, from documents or notes, or from a spreadsheet. Every operation is
billed to the user's Emboss account. The first 5 form creations, 5 context
fills, and 5 standard fills each month are free; free operations are limited
to 5-page forms. If Emboss tools are missing or a tool returns
insufficient_scope / unauthenticated, see SETUP.md in this folder, or
the emboss-setup skill in Claude Code.
Which tool
| User wants | Tool sequence |
|---|---|
| Make a flat PDF fillable | create_form, then get_form |
| Fill a form from values you already have | get_form (to see fields), then fill_form |
| Fill a form from a document, notes, or pasted text | fill_form_from_context, then poll get_job |
| Fill one form per row of a spreadsheet/CSV | suggest_mapping, confirm the mapping with the user, then fill_batch, then poll get_batch |
| Check remaining free operations or billing | get_usage |
| Reuse a form already uploaded | list_forms first, instead of create_form |
Rules
- Never invent field values. Only fill what the user gave you, or what a context document/CSV actually says.
- When
fill_formreturnsunmatched, show the user those labels and ask what to do with them; do not guess. - For choice fields, pick one of the options
get_formreturned (its label or value) rather than free text. - For checkboxes, pass
yesorno. fill_form_from_context,fill_batch, andget_batchcan take a while. Pollget_job/get_batchabout every 20 seconds and tell the user it is still running rather than going quiet.- Present every
download_urlas a plain link the user can click. - On a 402, relay the tool's
messageand point atbilling_url: forover_free_tierexplain that this month's free forms are used up; forover_page_capexplain that the form is over the 5-page free limit and a payment method is needed to continue. - On
unsupported_file, tell the user to export the document to PDF first; Emboss only accepts PDFs. - Never paste long context text back into the chat. Summarize what was sent (e.g. "sent the 2-page intake note as context") instead of quoting it in full.
- Only call
delete_formwhen the user explicitly asks to delete a form. It is permanent.
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.
- 4d ago First seen · 101 lines · 87 tokens per session scan A befacdd67ab4
emboss is a skill published in the GitHub repository GetEmboss-ai/emboss-claude-plugin (0 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 1,287 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 2026-08-31.
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.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.