transcript-to-pdf

transcript-to-pdf is a skill for Claude Code, Codex from Elumenotion/GuideAnts. It costs 71 tokens per session (1,128 once invoked), scanned A, original, Apache-2.0.

A tool that turns a recorded coding-agent conversation into a styled, print-ready PDF. PDF is a document format designed to preserve layout when shared or printed.

In plain words
What is it for?
Use it to export, archive, or share a GuideAnts or Code-Executor session as a polished PDF.
Why use it?
It gives conversation logs a consistent structure, including speaker turns, tool inputs, and highlighted code, instead of leaving them as plain text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to export, archive, or share a GuideAnts or Code-Executor session as a polished PDF.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elumenotion/guideants/transcript-to-pdf
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 Elumenotion/GuideAnts --skill transcript-to-pdf
Clone the repo
git clone --depth 1 https://github.com/Elumenotion/GuideAnts

Made for: Claude Code, Codex.

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 transcript-to-pdf

README.md
[![agentmods](https://agentmods.dev/badge/skills/elumenotion/guideants/transcript-to-pdf.svg)](https://agentmods.dev/skills/elumenotion/guideants/transcript-to-pdf)
Your own site
<a href="https://agentmods.dev/skills/elumenotion/guideants/transcript-to-pdf"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/transcript-to-pdf.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 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 $0.00071 $0.01128
Opus 5 $0.00036 $0.00564
Sonnet 5 $0.00014 $0.00226
Haiku 4.5 $0.00007 $0.00113

Measured 3d ago against content hash 1157de27d5ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

transcript-to-pdf 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/md_transcript_to_pdf.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

samples/skills/transcript-to-pdf/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

transcript-to-pdf

Paths — fixed layout, do not probe or re-derive. The sandbox CWD is the notebook's output directory. This skill's scripts live under Skills/transcript-to-pdf/scripts/ relative to it. Write PDF output with a bare filename (e.g. -o report.pdf); never prefix with Output/.

Turns a markdown conversation transcript (the kind produced by saving a GuideAnts / Code-Executor session) into a well-formatted PDF.

The renderer understands the transcript system, not generic markdown: it recognises **User** / **Assistant** / **Tool** turns, **Tool Call:** input blocks, and tool OUTPUT JSON, and lays each out as a distinct card. Heredoc script inputs (e.g. cat > file <<EOF) are split so the bash header and the written-file body are highlighted with the correct language lexer.

Stdlib + weasyprint only. No network. No model download. Runs in seconds.

Dependencies

Required (already present in the sandbox image):

weasyprint   # HTML -> PDF
pygments     # code highlighting
pypdf        # (optional) page inspection

Check with python3 -c "import weasyprint, pygments". If missing: pip install weasyprint pygments.

What to run

Single command, one input, one output:

python3 Skills/transcript-to-pdf/scripts/md_transcript_to_pdf.py \
  <transcript>.md -o <out>.pdf
  • Output defaults to <input>.pdf when -o is omitted.
  • The script prints a short report (title, turn counts, tool-call counts, fence fixes, output path) and exits 0 on success.

Useful flags

python3 .../md_transcript_to_pdf.py in.md --no-cover   # drop the cover page
python3 .../md_transcript_to_pdf.py in.md --html out.html   # also dump the intermediate HTML (debug)
python3 .../md_transcript_to_pdf.py in.md --quiet       # suppress the report

Layout guarantees

  • Cover page — title, subtitle, stat grid (messages / users / assistants / tool calls / heredocs / source lines), metadata table, and a list of the session's user requests. The list region is a bounded flex box (flex:1 1 0; min-height:0; overflow:hidden) so it cannot collide with the footer regardless of how long the session is. Snippets are capped (4 shown, "+ N more" otherwise) and shortened to ~140 chars to keep the common case clean.
  • Turns — every message is a role-badged card (User / Assistant / Tool).
  • Tool-call inputs**Tool Call:** blocks are anchored to the following JSON fence; the script field is unescaped and, if it is a heredoc, rendered as (bash header) + (file body in the right language) + (bash footer).
  • Tool outputs — the **Tool** result JSON renders in an amber panel.
  • Markdown — headings, bold/italic, inline code, lists, and pipe tables.
  • Truncated-fence repair — turns that end mid-code-fence get a closing fence inserted so the document balances.

Read the full file on GitHub · 121 lines

Files

What ships with it

2 files 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.

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. 3d ago First seen · 121 lines · 71 tokens per session scan A 1157de27d5ab

Subscribe to this mod's changes

transcript-to-pdf is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 1,128 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 2026-09-03.