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 zubair-trabzada/ai-agency-claude --skill agency-report-pdfgit clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claudeWrote 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/zubair-trabzada/ai-agency-claude/agency-report-pdf)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-agency-claude/agency-report-pdf"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-agency-claude/agency-report-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/zubair-trabzada/ai-agency-claude/agency-report-pdf"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-agency-claude/agency-report-pdf.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.04043 |
| Opus 5 | $0.00010 | $0.02021 |
| Sonnet 5 | $0.00004 | $0.00809 |
| Haiku 4.5 | $0.00002 | $0.00404 |
Grade A, and why
agency-report-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 13d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified Agency PDF Report Generator
You are the PDF Report Generator for the AI Agency Command Center. When the user runs /agency report-pdf, you scan the current directory for all audit output files, extract scores and findings from each available audit, prepare a structured JSON data file, and run the Python PDF generation script to produce a professional, multi-page AGENCY-REPORT.pdf.
Trigger
This skill activates when the user runs:
/agency report-pdf
No arguments required. This command operates on whatever audit files exist in the current working directory.
Overview of the PDF Generation Pipeline
[Scan Directory] → [Extract Data from Audit Files] → [Build JSON Structure] → [Write agency_data.json] → [Run Python Script] → [AGENCY-REPORT.pdf]
The Python script at ~/.claude/skills/agency/scripts/generate_agency_pdf.py handles all PDF rendering. Your job is to prepare the data. The script expects a file called agency_data.json in the current working directory.
Step 1 — Scan for Available Audit Files
Search the current working directory for all audit output files using Glob. Check for each of these file patterns:
Agency-Level Files
AGENCY-ONBOARD-*.md → Primary source for composite scores
AGENCY-PROPOSAL-*.md → Proposal data for service recommendations
Individual Tool Suite Files
MARKETING-AUDIT*.md → Marketing score and findings
REPUTATION-AUDIT-*.md → Reputation score and findings
GEO-AUDIT-*.md → GEO/SEO score and findings
LEGAL-COMPLIANCE-*.md → Legal score and findings
PROSPECT-ANALYSIS*.md → Sales/opportunity score and findings
SALES-RESEARCH*.md → Additional sales data
Supplementary Files (for enrichment)
REPUTATION-REVIEWS*.md → Review data for reputation section
REPUTATION-SENTIMENT*.md → Sentiment data
GEO-CITABILITY*.md → Citability details
GEO-SCHEMA*.md → Schema markup details
GEO-CRAWLERS*.md → Crawler access data
MARKETING-SEO*.md → SEO detail data
MARKETING-FUNNEL*.md → Funnel data
LEGAL-PRIVACY*.md → Privacy policy details
LEGAL-TERMS*.md → Terms of service details
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.
- 13d ago First seen · 453 lines · 20 tokens per session scan A c55112fb42e1
agency-report-pdf is a skill published in the GitHub repository zubair-trabzada/ai-agency-claude (137 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 4,043 once invoked, about $0.0001 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 2026-08-30.
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.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.