A tool that turns one SOP or flowchart into a PDF. An SOP is a written step-by-step procedure; a flowchart is a diagram showing decisions or process steps.

Use it to compile `.typ` documents or render `.mmd` Mermaid and `.d2` D2 flowcharts into output files.

It handles the separate rendering and compiling steps needed when a document includes Mermaid or D2 diagrams. It also checks whether the required command-line tools are installed.

compile — Skill for Claude Code by danielrosehill

Install

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.

Any agent

npx skills add danielrosehill/Claude-SOP-Writer-Plugin --skill compile

Clone the repo

git clone --depth 1 https://github.com/danielrosehill/Claude-SOP-Writer-Plugin

Made for: Claude Code.

Or install sop-writer, the plugin that ships this one along with the rest of its 6 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-sop-writer-plugin/compile/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-sop-writer-plugin/compile)

Your own site

<a href="https://agentmods.dev/skills/danielrosehill/claude-sop-writer-plugin/compile"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-sop-writer-plugin/compile/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danielrosehill/claude-sop-writer-plugin/compile"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-sop-writer-plugin/compile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 539 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00085	$0.00539
Opus 5	$0.00043	$0.00269
Sonnet 5	$0.00017	$0.00108
Haiku 4.5	$0.00009	$0.00054

Measured 8d ago against content hash 9b4680d4371d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compile 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 8d 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.

skills/compile/SKILL.md · 52 lines

What it actually says

compile

Render a single document to PDF. Project-scoped — operates on files in the current working directory.

Inputs to gather

Source path — the .typ, .mmd, or .d2 file to compile. Accept absolute or project-relative.
Output path (optional) — defaults to output/<source-stem>.pdf in the project root, creating output/ if missing.

What to do

If the source is a `.typ` file

Detect any sibling .mmd or .d2 files referenced by #image(...) in the Typst source. For each, render to SVG first (see flowchart steps below).

Run:

typst compile <source.typ> <output.pdf>

Report the output path and file size.

If the source is a `.mmd` file (Mermaid)

mmdc -i <source.mmd> -o <source-stem>.svg

Then compile the sibling .typ wrapper if one exists, or just leave the SVG.

If the source is a `.d2` file

d2 <source.d2> <source-stem>.svg

Same follow-up as Mermaid.

Pre-flight checks

command -v typst — if missing, tell the user to install it (cargo install typst-cli or distro package).
command -v mmdc — only required if any Mermaid sources exist; install via npm i -g @mermaid-js/mermaid-cli.
command -v d2 — only required if any D2 sources exist.

Notes

Don't auto-rebuild every doc in the project — this skill compiles one file. For batch-compiling everything in a project, the user can loop in shell or use bundle-binder (which compiles its inputs as a side effect).
If typst compile fails, surface the error verbatim — Typst's error messages are good and the user needs to see them.

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.

8d ago First seen · 52 lines · 85 tokens per session scan A 9b4680d4371d

Subscribe to this mod's changes

compile is a skill published in the GitHub repository danielrosehill/Claude-SOP-Writer-Plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 539 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.

Documents PDF

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.

K-Dense-AI/scientific-agent-skills · 56 tokens

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.

microsoft/agent-framework · 82 tokens

compile

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

compile

Inputs to gather

What to do

If the source is a `.typ` file

If the source is a `.mmd` file (Mermaid)

If the source is a `.d2` file

Pre-flight checks

Notes

What this file has done since we first saw it

Other skills, from other repositories

pydicom

foundry-hosted-agent-validation

skill-doc-delivery

pdf-extract-create-workflow

document-direct-python

pdf-text-extraction-fallback-85d5ca

compile

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

compile

Inputs to gather

What to do

If the source is a .typ file

If the source is a .mmd file (Mermaid)

If the source is a .d2 file

Pre-flight checks

Notes

What this file has done since we first saw it

Other skills, from other repositories

pydicom

foundry-hosted-agent-validation

skill-doc-delivery

pdf-extract-create-workflow

document-direct-python

pdf-text-extraction-fallback-85d5ca

If the source is a `.typ` file

If the source is a `.mmd` file (Mermaid)

If the source is a `.d2` file