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/xyruscode/ai-sync/pdfnpx skills add XyrusCode/ai-sync --skill pdfgit clone --depth 1 https://github.com/XyrusCode/ai-syncWhat 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 | $0.00070 | $0.01339 |
| Opus 5 | $0.00035 | $0.00669 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route Selection
| Route | Trigger | Route File |
|---|---|---|
| ReportLab (default) | All PDF creation requests | routes/reportlab.md |
| md2pdf | Convert swarm-assembled Markdown to PDF (gated, see below) | routes/md2pdf.md |
| Process | Work with existing PDFs (extract, merge, fill forms, etc.) | routes/process.md |
Output path: write to the path the user requested. If its directory is not
writable (e.g. a container path like /mnt/... that does not exist here), fall
back to ./outputs/ under the current working directory, create it, and report
the final path. Never fail just because a hardcoded absolute directory is missing.
When to use md2pdf (gate): only for a multi-section Markdown report
assembled by a swarm writing skill — i.e. there is a *.agent.final.md or
several *_sec{NN}.md files produced by sub-agents, with standard Markdown
footnotes ([^id] + [^id]: Title. Date. URL) for citations. For a one-off PDF
the user asks you to write, author it natively via the ReportLab route;
hand-authored layout is cleaner than converted Markdown.
MANDATORY: Read Route File Before Implementation
Before implementation, you MUST:
- Determine the route (ReportLab / md2pdf / Process)
- Read the route file (
routes/reportlab.md,routes/md2pdf.md, orroutes/process.md) - Only then proceed with implementation
This file (SKILL.md) contains constraints and principles. Route files contain how-to details.
When route files use {skill_path}, resolve it in Kimi CLI as:
PDF_SKILL_DIR="${KIMI_PDF_SKILL_DIR:-$(pwd)/.agents/skills/pdf}"
Then replace {skill_path} with "$PDF_SKILL_DIR" in commands.
Decision Rules
| User Says | Route |
|---|---|
| "Create a PDF", "Make a report", "Write a paper" | ReportLab |
| "Extract text from PDF", "Merge these PDFs", "Fill this form" | Process |
Dependencies
| Route | Libraries |
|---|---|
| ReportLab | pip install reportlab matplotlib |
| md2pdf | pip install markdown2 xhtml2pdf (pure Python, reuses ReportLab) |
| Process | pip install pikepdf pdfplumber |
| Visual QA | Managed pypdfium2 + Pillow |
What ships with it
12 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.
- LICENSE.txt 719 B
- routes/md2pdf.md 3.5 KB
- routes/process.md 6.2 KB
- routes/reportlab.md 13 KB
- scripts/cmd_extract.py 5.3 KB runs code
- scripts/cmd_form.py 8.2 KB runs code
- scripts/cmd_inspect.py 5.4 KB runs code
- scripts/cmd_meta.py 3.5 KB runs code
- scripts/cmd_pages.py 4.9 KB runs code
- scripts/md2pdf/citation_md.py 8.9 KB runs code
- scripts/md2pdf/md2pdf_convert.py 7.8 KB runs code
- scripts/pdf.py 11 KB runs code
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.
- yesterday First seen · 133 lines · 70 tokens per session scan A b5850d326b6f
pdf is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,339 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…