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 PandaDoc/mcp-server-guide --skill pandadoc-signing-velocitygit clone --depth 1 https://github.com/PandaDoc/mcp-server-guideWrote 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/pandadoc/mcp-server-guide/pandadoc-signing-velocity)<a href="https://agentmods.dev/skills/pandadoc/mcp-server-guide/pandadoc-signing-velocity"><img src="https://agentmods.dev/badge/skills/pandadoc/mcp-server-guide/pandadoc-signing-velocity/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/pandadoc/mcp-server-guide/pandadoc-signing-velocity"><img src="https://agentmods.dev/badge/skills/pandadoc/mcp-server-guide/pandadoc-signing-velocity.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 | $0.00056 | $0.01532 |
| Opus 5.5 | $0.00022 | $0.00613 |
| Sonnet 5.5 | $0.00011 | $0.00306 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
pandadoc-signing-velocity 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PandaDoc Signing Velocity & Pipeline Report
Status counts, time to sign, value in flight, and what is stuck — as one report.
Every number here is computed by you over a bounded set. There is no aggregation endpoint, so the honesty of this report depends entirely on stating what went into it.
Prerequisites
The PandaDoc MCP Server must be connected. Required tools: documents_list, documents_details_get.
If they are missing, say so and point at https://mcp.pandadoc.com.
The rule for this skill
Every figure ships with its sample size and its method. A single average with no denominator is worse than no average, because it reads as authoritative. If you computed time-to-sign over four documents, say "over 4 documents". If you capped the set, say where you stopped.
Workflow
Step 1: Count by status
documents_list per status, count: 100. Statuses worth counting for a pipeline view:
- In flight:
Sent,Viewed,Waiting for Approval,External Review - Finished:
Completed,Paid - Dead or stalled:
Declined,Expired,Rejected - Not started:
Draft
One call per status — the parameter takes a single string. If a status returns 100 results, more may exist; say the count is a floor rather than a total.
Step 2: Average time to sign
Only Completed and Paid documents have a duration. For each, you need:
date_sent— only indocuments_details_get, one call per documentrecipients[].signature_date— also only in details, one entry per recipient
The interval is date_sent → the latest non-null recipients[].signature_date. Not date_completed:
that is when the document closed, which is not when it was signed. Cap the number of detail calls
(30 is reasonable) and say if you capped.
A document with no non-null signature_date has no interval at all. That single rule is also what
keeps force-completed documents out: a document flipped via documents_status_change has
date_completed set but every recipients[].signature_date as null and signature fields
is_filled: false, so it contributes nothing to the average and must not be counted as signed.
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.
- 4d ago Changed · +13 lines 2b3fd5d33708
- 1mo ago First seen · 140 lines · 56 tokens per session scan A f57caebb2a88
pandadoc-signing-velocity is a skill published in the GitHub repository PandaDoc/mcp-server-guide (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,532 once invoked, about $0.0002 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 2026-09-16.
Other skills, from other repositories
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
html-ppt-weekly-report
OpenDesign's weekly growth review: stars, installs, activation — the number, the driver, and the recommended move. Built as a decision-grade data & finance deck for growth & product team.
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. This is the generic document-writing engine (tool surface, tagged-value shapes, fabrication rules). For the four standard NetClaw report…
documents
The Metabase-flavored Markdown grammar for documentwrite — the CommonMark subset, {% card %} embeds, {% entity %} links, ::: layout containers (flex / supporting / resize) and nesting rules, surgical edits and their limits, card clones, comments. Triggers — "create a document / report", "put prose beside a chart"…
network-report-documents
The four standard NetClaw document compositions — a change-record Word document from a real ServiceNow CR plus device state, an interface/config audit workbook from real device queries, an executive summary deck with an embedded topology diagram, and a required PDF form filled from real data. Use when an operator asks…
reporting
Use when a recurring report must ship itself on a cadence — weekly digest, monthly exec pack, board pack — via a fetch→narrate→render→deliver pipeline with a schedule and a freshness gate. NOT a live view people slice (that is dashboard), NOT picking which KPIs to track (that is kpi-framework), NOT a one-off…