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 skills add me2resh/apexyard --skill pdfgit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/pdf)<a href="https://agentmods.dev/skills/me2resh/apexyard/pdf"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/pdf/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/me2resh/apexyard/pdf"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/pdf.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 | $0.00037 | $0.03103 |
| Opus 5.5 | $0.00015 | $0.01241 |
| Sonnet 5.5 | $0.00007 | $0.00621 |
| Haiku 4.5 | $0.00004 | $0.00310 |
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 22d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.
/pdf — Export Any Doc to PDF
Convert a framework-generated document (markdown, HTML, BPMN) to PDF for sharing with non-technical stakeholders, board members, customers, or auditors.
Sits alongside /c4 (Mermaid markdown), /dfd (Mermaid markdown), /tech-vision (markdown), /write-spec (PRD markdown), /journey (self-contained HTML), /process (BPMN XML), and the audit family (/threat-model, /launch-check, etc., all of which write dated markdown audits). Those skills emit a single source-of-truth artefact in its native format; /pdf is the dedicated bridge to PDF for the moments when prose isn't enough.
The destination question
A PDF can land in one of two places, and the answer depends on whether the doc should travel with the code if the project spun out tomorrow. This mirrors the existing rule in docs/multi-project.md:
| If YES (travels with the code) | If NO (ApexYard's view) |
|---|---|
Project's own repo: workspace/<name>/docs/ |
Ops fork: projects/<name>/pdfs/ |
| Examples: API spec, deployment runbook, internal sequence | Examples: handover assessment, stakeholder update, launch-check verdict |
The skill asks, doesn't guess. The 4-option prompt below covers every common case.
Usage
/pdf projects/sample-app/architecture/vision.md
/pdf workspace/sample-app/docs/architecture/context.md
/pdf projects/sample-app/audits/security/2026-05-19.md
/pdf projects/sample-app/journeys/checkout-v2.html
/pdf projects/sample-app/processes/onboarding.bpmn
/pdf <input> --no-prompt # use default_destination from config
/pdf <input> --converter=pandoc # force a specific converter
/pdf <input> --destination=workspace # skip the prompt, write to workspace/<name>/docs/
/pdf <input> --destination=projects # skip the prompt, write to projects/<name>/pdfs/
/pdf <input> --destination=keep # skip the prompt, keep next to source
/pdf <input> --destination=/absolute/path/out.pdf # explicit path
/pdf <input> --project=sample-app # override auto-detected project name
What ships with it
3 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.
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.
- 22d ago Changed · -2 lines 07fdaaf2defa
- 29d ago Changed · +6 lines f5e42d784841
- 1mo ago Changed · +4 lines 6471e5f3a4c7
- 2mo ago First seen · 257 lines · 37 tokens per session scan A c80831b7e3e6
pdf is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 3,103 once invoked, about $0.0001 per session on Opus 5.5. 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.
pdf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pdfme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 37 | Claude Code |
| add-pdf-reportmicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 30 | Claude Code |
| add-pdf-viewermicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 47 | Claude Code |
| compile-latexpedrohcgs/claude-code-my-workflow | Skill | 1.7k | 2d ago | MIT | A | 73 | Claude Code |
| moai-docs-generationmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 56 | Claude Code |
| blueprint-ask-answerreceptron/mulmoterminal | Skill | 261 | yesterday | MIT | A | 36 | Claude Code, Codex |
| product-spec-pdf-parserAlpacaLabsLLC/skills-for-architects | Skill | 402 | 3d ago | MIT | A | 45 | Claude Code |