preflight-demo

preflight-demo is a skill for Claude Code from katekruger/campaign-preflight. It costs 118 tokens per session (683 once invoked), scanned A, original, MIT.

A demonstration skill for campaign-preflight, a checker that reviews outbound email campaigns before sending.

In plain words
What is it for?
It runs a deliberately broken sample campaign and explains findings such as unsubscribed contacts, broken links, merge-field errors, and sender-capacity problems.
Why use it?
It lets you see a sample report and the kinds of problems the checker can catch before preparing your own data.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the campaign-preflight plugin — 3 skills, 1 MCP server shipped together

Good fit It runs a deliberately broken sample campaign and explains findings such as unsubscribed contacts, broken links, merge-field errors, and sender-capacity problems.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add katekruger/campaign-preflight
Claude Code
/plugin install campaign-preflight

Made for: Claude Code.

Or install campaign-preflight, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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 preflight-demo

README.md
[![agentmods](https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-demo/github.svg)](https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-demo)
Your own site
<a href="https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-demo"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-demo/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.

agentmods 80×15 button for preflight-demo

Your own site · 80×15
<a href="https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-demo"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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.
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 $0.00118 $0.00683
Opus 5 $0.00059 $0.00342
Sonnet 5 $0.00024 $0.00137
Haiku 4.5 $0.00012 $0.00068

Measured 10d ago against content hash 3aeb1f39f2e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

preflight-demo 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 10d 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.

skills/preflight-demo/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show the demo

Run the bundled demo and walk the user through what it caught.

"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo

Takes about a fiftieth of a second. No credentials, no network, no setup.

What the demo campaign contains

Twenty synthetic contacts and a three-step sequence, broken on purpose so one run demonstrates every kind of result. Highlights worth pointing out:

  • Stop-on-reply is off on a three-step sequence — repliers keep getting follow-ups.
  • A contact who unsubscribed is still on the list, and another is at a domain that opted out entirely.
  • Prompt-injection text sitting in a personalization field, scraped in from a page the target controls, queued to send under the user's domain.
  • An unrendered {{first_name}} that never merged.
  • A greeting addressed to the wrong person — the signature of a mis-joined enrichment table.
  • A TODO and a broken link still in the copy.
  • One sender with no health score and no daily limit, which is why sender capacity comes back UNKNOWN.

The point to land

That last one is the interesting one, and it is worth drawing attention to.

Most tools would add up the two senders that do report a limit and print a capacity number. This one reports UNKNOWN and names the mailbox it could not assess — and drops confidence from HIGH to MEDIUM because of it.

Say it roughly this way:

Notice the last section. It's not claiming the senders are fine and it's not claiming they're broken — it's saying it couldn't tell, and which one it couldn't tell about. A checker that can't distinguish "I looked and it's fine" from "I couldn't look" will eventually turn a permissions error into a green light.

Other formats, if asked

"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo --format markdown   # to paste into a doc
"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo --verbose           # explanations + score arithmetic

Then offer the obvious next step

Read the full file on GitHub · 68 lines

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. 10d ago First seen · 68 lines · 118 tokens per session scan A 3aeb1f39f2e6

Subscribe to this mod's changes

preflight-demo is a skill published in the GitHub repository katekruger/campaign-preflight (0 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 683 once invoked, about $0.0006 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.